© 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. 13468
    Prev
    Next
    INDEX
    Explanations

    terms related to political figures and campaigns

    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
    393
    +0.31
    1.6%
    36
    +0.23
    1.2%
    640
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.31
    0.31
    159
    +0.23
    0.14
    393
    +0.15
    0.17
    Negative Logits
     Jagu
    -0.76
    AIDS
    -0.76
    advertisement
    -0.74
    Edit
    -0.73
    anamo
    -0.73
    acid
    -0.72
    Ingredients
    -0.70
    evidence
    -0.69
    achu
    -0.69
    books
    -0.69
    POSITIVE LOGITS
     lot
    1.20
    cknowled
    1.14
     handful
    1.10
     couple
    1.08
    rouse
    1.07
     few
    1.07
     bunch
    1.03
     combination
    0.93
     mere
    0.91
     huge
    0.91
    Activations Density 3.162%

    No Known Activations