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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13231
    Prev
    Next
    INDEX
    Explanations

    words related to legal and government documents or names of countries

    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
    288
    +0.20
    0.7%
    211
    +0.17
    0.6%
    314
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.20
    0.06
    314
    +0.17
    0.00
    288
    +0.14
    0.08
    Negative Logits
    uncture
    -0.98
    aunder
    -0.95
    selves
    -0.94
    dfx
    -0.91
    heet
    -0.86
    afort
    -0.85
     Gleaming
    -0.82
     Logged
    -0.81
    oral
    -0.81
     Taken
    -0.81
    POSITIVE LOGITS
    querque
    1.70
    rows
    1.47
    rito
    1.42
    rowing
    1.33
    ger
    1.32
    geoning
    1.30
    leigh
    1.19
    row
    1.19
    geons
    1.19
    lington
    1.16
    Activations Density 1.735%

    No Known Activations