© 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. 35162
    Prev
    Next
    INDEX
    Explanations

    descriptions of sports games and events, especially focusing on game flow, scores, and team performance

    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
    0.9%
    259
    +0.11
    0.5%
    214
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.18
    0.17
    608
    +0.11
    0.20
    635
    +0.11
    0.09
    Negative Logits
     concess
    -0.76
    cise
    -0.66
     indict
    -0.60
    dain
    -0.60
     arra
    -0.59
    Anth
    -0.59
     ghetto
    -0.58
    School
    -0.57
    tan
    -0.56
    Grade
    -0.55
    POSITIVE LOGITS
     margin
    0.71
     bluff
    0.69
    manship
    0.68
     midway
    0.65
    beat
    0.63
     proport
    0.61
    kick
    0.61
     mentality
    0.61
    otaur
    0.60
    boa
    0.60
    Activations Density 15.242%

    No Known Activations