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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34562
    Prev
    Next
    INDEX
    Explanations

    language related to politics, international relations, and diplomatic activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.23
    1.2%
    327
    +0.09
    0.5%
    523
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.23
    0.21
    408
    +0.09
    0.23
    608
    +0.09
    0.25
    Negative Logits
    ').
    -0.67
    !'
    -0.65
    )--
    -0.65
    schild
    -0.62
    ategor
    -0.61
    .--
    -0.60
    ?'
    -0.60
     afore
    -0.58
    .—
    -0.58
    !'"
    -0.57
    POSITIVE LOGITS
    ¬¼
    0.73
     "
    0.71
     "[
    0.70
     anecd
    0.69
    wcs
    0.66
     "â̦
    0.65
     "...
    0.63
     "#
    0.63
     misunderstood
    0.58
     underestimated
    0.57
    Activations Density 29.293%

    No Known Activations