© 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. 34850
    Prev
    Next
    INDEX
    Explanations

    descriptions of specific plays and game situations in sports matches

    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
    +0.21
    1.1%
    481
    +0.10
    0.5%
    384
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.21
    0.07
    460
    +0.10
    0.10
    384
    +0.10
    0.07
    Negative Logits
    itarian
    -0.70
    sonian
    -0.69
    protein
    -0.63
    Sov
    -0.62
    Property
    -0.60
    Bone
    -0.59
    verified
    -0.59
    living
    -0.59
    breeding
    -0.58
     welf
    -0.58
    POSITIVE LOGITS
     runoff
    0.62
     replay
    0.62
     kickoff
    0.61
     halftime
    0.61
    imester
    0.60
     Huck
    0.60
    ftime
    0.58
    INAL
    0.58
    finals
    0.56
     Darrell
    0.56
    Activations Density 11.608%

    No Known Activations