© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 3173
    Prev
    Next
    INDEX
    Explanations

    references to professional sports leagues, mainly the NFL and NBA

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    706
    +0.14
    0.6%
    541
    +0.13
    0.5%
    288
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.20
    11
    +0.13
    0.08
    652
    +0.13
    0.09
    Negative Logits
    antry
    -0.86
    ãĥ´ãĤ¡
    -0.74
    shapeshifter
    -0.71
    ordering
    -0.71
     Ples
    -0.70
    reads
    -0.70
    vet
    -0.69
     Rate
    -0.69
    utter
    -0.69
    ainer
    -0.68
    POSITIVE LOGITS
     stadiums
    1.10
     soccer
    1.04
     baseball
    1.02
     stadium
    0.98
     football
    0.98
     basketball
    0.95
     hockey
    0.91
     rugby
    0.90
    Fan
    0.89
     cricket
    0.89
    Activations Density 4.226%

    No Known Activations