© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45769
    Prev
    Next
    INDEX
    Explanations

    information related to sports teams and players

    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
    +0.20
    0.9%
    31
    +0.14
    0.6%
    49
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.20
    0.03
    31
    +0.14
    0.08
    561
    +0.09
    0.07
    Negative Logits
    bent
    -0.69
    cry
    -0.69
     drip
    -0.67
     ILCS
    -0.65
    bart
    -0.63
    abbage
    -0.62
    Cart
    -0.61
    products
    -0.61
    rir
    -0.61
    trigger
    -0.60
    POSITIVE LOGITS
     coached
    0.81
     rosters
    0.76
     coach
    0.73
     fullback
    0.72
     lineup
    0.71
    Coach
    0.70
     roster
    0.69
     mates
    0.67
     coaches
    0.67
    eers
    0.66
    Activations Density 6.319%

    No Known Activations