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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 32321
    Prev
    Next
    INDEX
    Explanations

    references to people named "Walker" particularly in relation to sports, politics, and legal matters

    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
    +0.21
    1.1%
    683
    +0.10
    0.5%
    326
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.21
    0.08
    353
    +0.10
    0.06
    224
    +0.09
    0.08
    Negative Logits
    ritic
    -0.77
     Seym
    -0.74
    undai
    -0.70
     mathemat
    -0.69
    sembly
    -0.69
    romeda
    -0.69
    ificant
    -0.65
     rul
    -0.65
    eon
    -0.65
    enta
    -0.64
    POSITIVE LOGITS
    stown
    0.71
    Walker
    0.69
    inson
    0.69
     Walker
    0.68
    esque
    0.66
    ball
    0.65
    tip
    0.64
    chairs
    0.62
    king
    0.61
    mania
    0.59
    Activations Density 6.496%

    No Known Activations