© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 9294
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports game statistics and analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    260
    +0.11
    0.5%
    491
    +0.10
    0.5%
    366
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    567
    +0.11
    0.03
    36
    +0.10
    0.03
    102
    +0.10
    0.03
    Negative Logits
    idth
    -0.78
    !/
    -0.73
    ength
    -0.72
     Mub
    -0.63
     Cosponsors
    -0.61
     provoked
    -0.60
    enery
    -0.60
    accompan
    -0.59
     demonstrations
    -0.59
     snippets
    -0.59
    POSITIVE LOGITS
     worthwhile
    0.88
     attractive
    0.85
     viable
    0.79
    competitive
    0.76
     desirable
    0.75
     formidable
    0.73
    haus
    0.73
     moot
    0.71
     richer
    0.71
     manageable
    0.71
    Activations Density 0.119%

    No Known Activations