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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13907
    Prev
    Next
    INDEX
    Explanations

    book titles and references to them

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    651
    +0.14
    0.5%
    345
    +0.14
    0.5%
    292
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.14
    0.10
    644
    +0.14
    0.08
    419
    +0.13
    0.08
    Negative Logits
    hap
    -1.09
    yg
    -1.01
    wang
    -0.97
    od
    -0.96
    cream
    -0.94
     distant
    -0.93
    vantage
    -0.92
    ensen
    -0.91
    bred
    -0.91
    oling
    -0.89
    POSITIVE LOGITS
    stores
    1.27
     titled
    1.18
    izations
    1.15
    seller
    1.06
    isations
    1.04
     [|
    1.04
     Notting
    1.00
    Ô
    0.99
    store
    0.99
     anthology
    0.99
    Activations Density 1.360%

    No Known Activations