© 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. 832
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms, including mathematical concepts and physical descriptions

    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
    640
    +0.34
    1.7%
    480
    +0.19
    1.0%
    160
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.34
    0.17
    107
    +0.19
    0.16
    160
    +0.17
    0.17
    Negative Logits
     frontline
    -0.84
     payroll
    -0.77
     weekend
    -0.76
     ousted
    -0.73
     embassy
    -0.71
     funnel
    -0.68
     inauguration
    -0.68
     migration
    -0.68
     nightly
    -0.68
     Mobil
    -0.68
    POSITIVE LOGITS
    Contents
    1.44
    Examples
    1.43
    Trivia
    1.43
    Anyway
    1.39
    Example
    1.38
    Rated
    1.38
    Advertisements
    1.37
    Reviewer
    1.36
    Sometimes
    1.36
    Secondly
    1.33
    Activations Density 0.517%

    No Known Activations