© 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. 13675
    Prev
    Next
    INDEX
    Explanations

    words related to cooking and food preparation, such as ingredients, cooking methods, and dishes

    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
    +0.29
    1.7%
    729
    +0.09
    0.5%
    470
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.29
    0.16
    553
    +0.09
    0.07
    271
    +0.08
    0.04
    Negative Logits
     ravaged
    -0.52
    NetMessage
    -0.49
    dimension
    -0.49
     bowel
    -0.46
    weeney
    -0.45
     deteriorated
    -0.45
    ujah
    -0.45
     repaired
    -0.44
     orderly
    -0.44
     restless
    -0.44
    POSITIVE LOGITS
     haha
    0.62
    EEE
    0.60
     because
    0.58
     anymore
    0.56
     Luxem
    0.56
    !?
    0.55
    soType
    0.54
     unless
    0.54
     underest
    0.54
    PLIED
    0.53
    Activations Density 22.324%

    No Known Activations