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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 0-ATT-KK
    6. 14020
    Prev
    Next
    INDEX
    Explanations

    information related to the size or scale of something, particularly in terms of being the largest

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L0_Hcat_z_lr1.20e-03_l11.80e+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.0.attn.hook_z
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.19
    2:0.05
    3:0.17
    4:0.11
    5:0.13
    6:0.03
    7:0.06
    8:0.05
    9:0.05
    10:0.07
    11:0.03
    Negative Logits
    bara
    -3.79
    patient
    -3.71
    nee
    -3.64
    ITNESS
    -3.62
    ordan
    -3.53
    pton
    -3.37
    vous
    -3.30
    venge
    -3.29
    olog
    -3.28
    fits
    -3.28
    POSITIVE LOGITS
    avorite
    3.87
     citiz
    3.86
    TextColor
    3.86
    vier
    3.76
    wcs
    3.71
    ��
    3.68
     "$:/
    3.65
    daq
    3.58
    enary
    3.50
     サーティワン
    3.44
    Activations Density 0.005%

    No Known Activations