© 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 24576
    9. 8-RES_FS24576-JB
    11. 1520
    Prev
    Next
    INDEX
    Explanations

    names or mentions related to a person named "Shel" or "Shelton"

    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
    119
    +0.11
    0.5%
    742
    +0.11
    0.5%
    564
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.11
    0.01
    299
    +0.11
    0.01
    232
    +0.10
    0.01
    Negative Logits
    Rated
    -0.68
    ERC
    -0.66
     entangled
    -0.62
     Debor
    -0.62
    Effective
    -0.60
    ALLY
    -0.59
    EED
    -0.59
    reme
    -0.58
     nomine
    -0.58
    print
    -0.57
    POSITIVE LOGITS
    tered
    0.94
    mand
    0.91
    angelo
    0.90
    ibrary
    0.88
    iflower
    0.88
    nikov
    0.83
    itably
    0.82
    ieu
    0.81
    oad
    0.81
    itism
    0.80
    Activations Density 0.018%

    No Known Activations