Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10651
    Prev
    Next
    INDEX
    Explanations

    social media references and engagement metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    attends to the first token of a person's name from a pronoun or other mention of the person later in the sequence.

    oai_attention-head · gemini-1.5-proTriggered by @danielepoterti
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.06
    3:0.05
    4:0.06
    5:0.05
    6:0.18
    7:0.06
    8:0.08
    9:0.26
    10:0.03
    11:0.04
    Negative Logits
     Wyr
    -4.05
     Nib
    -3.63
     Scar
    -3.47
     Scrolls
    -3.46
     McF
    -3.38
    ritch
    -3.37
    TEXTURE
    -3.29
    tes
    -3.18
    Sky
    -3.18
     irrad
    -3.17
    POSITIVE LOGITS
     Joan
    9.68
    Jo
    4.41
     Lisbon
    4.18
     Fran
    3.88
     Manit
    3.85
     Jeanne
    3.78
     Henri
    3.74
     Jo
    3.74
     Peggy
    3.64
     Margaret
    3.63
    Activations Density 0.000%

    No Known Activations