© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1598
    Prev
    Next
    INDEX
    Explanations

    credit or acknowledgment of contribution in a written context

    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
    49
    +0.10
    0.4%
    745
    +0.10
    0.4%
    41
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.07
    121
    +0.10
    0.06
    257
    +0.10
    0.04
    Negative Logits
    genre
    -0.69
    information
    -0.68
    ine
    -0.65
    erate
    -0.64
    ace
    -0.63
     denies
    -0.62
     innoc
    -0.60
    elligent
    -0.59
    andi
    -0.58
    of
    -0.58
    POSITIVE LOGITS
     whom
    0.89
     Lifetime
    0.71
    pload
    0.68
     Infinite
    0.68
     Prague
    0.65
     Shap
    0.64
     Galile
    0.63
     Ov
    0.63
     Depth
    0.62
    ĸļ
    0.62
    Activations Density 0.657%

    No Known Activations