© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7627
    Prev
    Next
    INDEX
    Explanations

    phrases related to political corruption and the influence of money in politics

    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
    739
    +0.14
    0.6%
    578
    +0.11
    0.5%
    742
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.06
    2
    +0.11
    0.02
    567
    +0.11
    0.03
    Negative Logits
    stocks
    -0.81
    ework
    -0.76
    esc
    -0.72
    ocks
    -0.71
    els
    -0.68
    resh
    -0.68
    inks
    -0.68
    ĺħ
    -0.65
    IELD
    -0.64
    ek
    -0.64
    POSITIVE LOGITS
     bluff
    0.77
     Clicker
    0.77
     Parenthood
    0.76
     Crusade
    0.72
    ridor
    0.72
     Interstate
    0.67
     PACs
    0.67
     Lobby
    0.67
     Maze
    0.66
     Triangle
    0.66
    Activations Density 0.378%

    No Known Activations