© 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. 40026
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific terms related to historical events, political movements, and individuals

    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
    432
    +0.08
    0.5%
    222
    +0.08
    0.5%
    194
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    432
    +0.08
    0.07
    26
    +0.08
    0.08
    255
    +0.07
    0.06
    Negative Logits
    encia
    -0.57
    imester
    -0.57
    shed
    -0.50
    agos
    -0.49
    assium
    -0.48
    iev
    -0.47
    emia
    -0.47
    ãĥł
    -0.47
    ãĤª
    -0.46
    éĸ
    -0.46
    POSITIVE LOGITS
    neys
    0.61
    geist
    0.53
     Rowling
    0.52
    aline
    0.52
    strap
    0.51
    yll
    0.49
    uple
    0.49
    ilee
    0.49
    unal
    0.47
    ones
    0.47
    Activations Density 5.689%

    No Known Activations