© 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 49152
    9. 8-RES_FS49152-JB
    11. 37314
    Prev
    Next
    INDEX
    Explanations

    entities associated with legal and governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    659
    +0.10
    0.5%
    620
    +0.10
    0.5%
    500
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.05
    232
    +0.10
    0.04
    325
    +0.09
    0.04
    Negative Logits
    iatus
    -0.59
    à©
    -0.57
    ggle
    -0.56
    akeru
    -0.53
     lazy
    -0.53
    oké
    -0.53
    emort
    -0.52
    romeda
    -0.52
    aspberry
    -0.51
    OHN
    -0.50
    POSITIVE LOGITS
    +.
    0.81
     Edition
    0.76
    $.
    0.74
     notwithstanding
    0.69
     respectively
    0.69
    .).
    0.69
    %.
    0.69
    !.
    0.69
    *.
    0.67
    _.
    0.67
    Activations Density 0.369%

    No Known Activations