© 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
    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. 3661
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and activities, particularly focusing on baseball, basketball, hockey, and football

    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
    247
    +0.09
    0.5%
    498
    +0.08
    0.4%
    453
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.22
    326
    +0.08
    0.20
    11
    +0.08
    0.07
    Negative Logits
    ktop
    -0.65
    ãĥ´ãĤ¡
    -0.63
    Dialogue
    -0.59
    ahead
    -0.58
    utter
    -0.57
    idency
    -0.56
    fab
    -0.56
    DonaldTrump
    -0.55
    ancies
    -0.55
    ãĥ´
    -0.54
    POSITIVE LOGITS
     Doodle
    0.73
     soccer
    0.71
     baseball
    0.69
     basketball
    0.67
     volleyball
    0.67
     rink
    0.66
     hockey
    0.65
     moms
    0.61
    bowl
    0.60
     cricket
    0.58
    Activations Density 7.812%

    No Known Activations