© 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 12288
    9. 8-RES_FS12288-JB
    11. 10226
    Prev
    Next
    INDEX
    Explanations

    references to historical events and political actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    747
    +0.12
    0.5%
    559
    +0.11
    0.5%
    599
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    747
    +0.12
    0.04
    689
    +0.11
    0.06
    598
    +0.09
    0.04
    Negative Logits
    wind
    -0.67
    etc
    -0.64
    rup
    -0.61
     syndrome
    -0.57
    bats
    -0.57
    hound
    -0.56
    tz
    -0.56
    ATA
    -0.56
    aud
    -0.55
    terson
    -0.54
    POSITIVE LOGITS
     principally
    0.90
     includ
    0.84
     chiefly
    0.81
     primarily
    0.81
    accompanied
    0.78
     accompanied
    0.78
     mainly
    0.77
    mostly
    0.77
     invariably
    0.75
     mostly
    0.75
    Activations Density 1.016%

    No Known Activations