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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4356
    Prev
    Next
    INDEX
    Explanations

    punctuation marks signaling a contrast or transition in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "However."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULAR
    -0.74
    SourceFile
    -0.70
    pecially
    -0.67
    ni
    -0.65
    ige
    -0.62
    SI
    -0.62
    pack
    -0.61
    grand
    -0.61
    arez
    -0.60
    rolled
    -0.60
    POSITIVE LOGITS
     unlike
    1.06
     alas
    1.05
     beware
    0.94
    chery
    0.88
     according
    0.86
     insofar
    0.85
     interestingly
    0.82
     despite
    0.81
     there
    0.80
     nevertheless
    0.79
    Activations Density 0.085%

    No Known Activations