© 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. 39999
    Prev
    Next
    INDEX
    Explanations

    actions or movements described in technical or instructional text

    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
    +0.18
    0.8%
    270
    +0.13
    0.6%
    240
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.18
    0.06
    553
    +0.13
    0.06
    549
    +0.11
    0.06
    Negative Logits
    eries
    -0.75
    antry
    -0.69
    cious
    -0.67
     tyr
    -0.65
    mint
    -0.63
    interstitial
    -0.62
    okers
    -0.60
    olean
    -0.60
    itational
    -0.60
     turnover
    -0.59
    POSITIVE LOGITS
    wards
    1.27
    stretched
    1.17
    fitted
    1.03
    flows
    0.98
    doors
    0.96
    )=(
    0.90
    casts
    0.87
    skirts
    0.86
    bur
    0.85
    bound
    0.85
    Activations Density 7.070%

    No Known Activations