© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14839
    Prev
    Next
    INDEX
    Explanations

    words related to personal actions or self-referential behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to self-identification or self-involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.78
    heny
    -0.77
    ulton
    -0.73
    artisan
    -0.73
    illery
    -0.72
    microsoft
    -0.72
    cemic
    -0.70
    apple
    -0.69
    sweet
    -0.69
    rought
    -0.68
    POSITIVE LOGITS
     tremend
    0.85
     profess
    0.79
    selves
    0.75
     underwater
    0.75
    åĤ
    0.73
     submar
    0.71
     ens
    0.70
     personally
    0.69
     worshipped
    0.68
     creatively
    0.67
    Activations Density 0.048%

    No Known Activations