© 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. 45740
    Prev
    Next
    INDEX
    Explanations

    names of actors and movie titles

    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
    +0.22
    1.0%
    589
    +0.11
    0.5%
    673
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.22
    0.31
    640
    +0.11
    0.26
    673
    +0.11
    0.10
    Negative Logits
     deval
    -0.75
    WARN
    -0.74
     econom
    -0.73
    ctory
    -0.72
    osate
    -0.72
    ģ«
    -0.72
    payer
    -0.70
     depreciation
    -0.69
     ration
    -0.69
     futile
    -0.68
    POSITIVE LOGITS
     actress
    1.07
     actresses
    1.04
     actor
    1.03
     Ghostbusters
    1.02
     vocals
    0.99
     Comedy
    0.99
     Scenes
    0.99
     Cartoon
    0.97
     Actress
    0.95
     actors
    0.95
    Activations Density 12.445%

    No Known Activations