© 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 Local
    9. 6-RES_SCL-AJT
    11. 40772
    Prev
    Next
    INDEX
    Explanations

    words related to politics, government, and current events

    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
    323
    +0.11
    0.5%
    322
    +0.11
    0.5%
    50
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.11
    0.08
    111
    +0.11
    0.06
    192
    +0.11
    0.05
    Negative Logits
    owship
    -0.75
    cliffe
    -0.72
    quartered
    -0.69
    agara
    -0.68
    enegger
    -0.66
    utical
    -0.65
    omez
    -0.62
    igans
    -0.61
    inki
    -0.60
    zik
    -0.60
    POSITIVE LOGITS
    lisher
    0.88
    ©¶æ
    0.75
    heid
    0.75
    oros
    0.74
    entimes
    0.73
    monary
    0.73
    Wan
    0.72
    ansion
    0.69
    gres
    0.69
    Desk
    0.69
    Activations Density 8.238%

    No Known Activations