© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 8032
    Prev
    Next
    INDEX
    Explanations

    sections referring to specific events and their aftermath in a narrative 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_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
    36
    +0.24
    1.1%
    314
    +0.12
    0.6%
    159
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.24
    0.08
    608
    +0.12
    0.05
    298
    +0.12
    0.04
    Negative Logits
    adding
    -0.75
    evidence
    -0.72
    packages
    -0.70
    items
    -0.69
     indicators
    -0.69
    casts
    -0.65
    letters
    -0.64
    ador
    -0.64
     Examples
    -0.63
     Occupations
    -0.63
    POSITIVE LOGITS
    venge
    1.32
    rouse
    1.03
     conclusion
    0.89
     manageable
    0.88
     whopping
    0.86
     rainy
    0.84
     halt
    0.83
     predetermined
    0.83
     convenient
    0.82
     satisfactory
    0.81
    Activations Density 0.115%

    No Known Activations