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. 13505
    Prev
    Next
    INDEX
    Explanations

    information related to legal and governmental regulations

    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
    450
    +0.06
    0.5%
    93
    +0.05
    0.4%
    765
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.06
    0.32
    6
    +0.05
    0.19
    107
    +0.05
    0.06
    Negative Logits
     shocks
    -0.35
    icter
    -0.35
    chuk
    -0.34
    fork
    -0.33
    axe
    -0.33
    ouver
    -0.33
    qt
    -0.33
     trouble
    -0.33
     Gaul
    -0.32
    henko
    -0.32
    POSITIVE LOGITS
    Reviewer
    0.41
    Privacy
    0.41
    glers
    0.40
    rha
    0.39
    Msg
    0.38
    abilia
    0.37
    ascript
    0.37
    rency
    0.36
    rity
    0.36
    pta
    0.35
    Activations Density 13.828%

    No Known Activations