© 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. 14123
    Prev
    Next
    INDEX
    Explanations

    mutations in genetic sequences

    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
    +0.11
    0.7%
    288
    +0.10
    0.6%
    78
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.17
    724
    +0.10
    0.12
    575
    +0.08
    0.12
    Negative Logits
    english
    -0.69
    ħĭ
    -0.59
    ¥µ
    -0.57
     Aires
    -0.53
    ¾
    -0.53
    ¬¼
    -0.52
    é¾įåĸļ士
    -0.52
    quarters
    -0.51
     Territories
    -0.51
    CHA
    -0.50
    POSITIVE LOGITS
     mutation
    0.77
    uating
    0.63
    utation
    0.63
     mutations
    0.62
     predis
    0.60
     allele
    0.56
     occurring
    0.55
    uation
    0.55
    icides
    0.54
     occur
    0.54
    Activations Density 3.034%

    No Known Activations