© 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. 7208
    Prev
    Next
    INDEX
    Explanations

    contributions to news reports

    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
    591
    +0.12
    0.6%
    214
    +0.11
    0.5%
    412
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.12
    0.02
    591
    +0.11
    0.02
    214
    +0.09
    0.02
    Negative Logits
    Mods
    -0.77
     Majesty
    -0.72
     horr
    -0.68
     peers
    -0.65
    AppData
    -0.63
    é¾įå¥ij士
    -0.62
    stones
    -0.60
     Maiden
    -0.60
     dumps
    -0.60
    cum
    -0.59
    POSITIVE LOGITS
    inion
    0.87
    otaur
    0.74
    ogh
    0.72
    swick
    0.70
    olicy
    0.69
    acas
    0.68
     Tribune
    0.65
    anamo
    0.63
    cerpt
    0.63
    rike
    0.62
    Activations Density 0.059%

    No Known Activations