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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34798
    Prev
    Next
    INDEX
    Explanations

    references to genius or exceptional abilities

    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
    +0.23
    1.1%
    288
    +0.11
    0.5%
    294
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.20
    111
    +0.11
    0.08
    99
    +0.10
    0.09
    Negative Logits
    aver
    -0.69
    den
    -0.66
     Continued
    -0.65
    than
    -0.65
    hold
    -0.64
    eper
    -0.63
    etch
    -0.63
    ¼
    -0.62
    Lago
    -0.62
    ¶
    -0.61
    POSITIVE LOGITS
     genius
    0.78
    ulously
    0.78
     Doodle
    0.75
     thesis
    0.73
    ocratic
    0.70
    ocrats
    0.69
     stroke
    0.69
    stroke
    0.67
     brilliance
    0.66
    smanship
    0.66
    Activations Density 6.946%

    No Known Activations