© 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. 22013
    Prev
    Next
    INDEX
    Explanations

    concerns related to disagreements and doubts

    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
    107
    +0.09
    0.4%
    626
    +0.09
    0.4%
    567
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.09
    0.03
    200
    +0.09
    0.02
    616
    +0.09
    0.02
    Negative Logits
     doubtless
    -0.80
    ription
    -0.73
    uta
    -0.70
    lesi
    -0.67
    only
    -0.65
    rimination
    -0.65
     merely
    -0.64
     likewise
    -0.63
    utenberg
    -0.63
    afort
    -0.62
    POSITIVE LOGITS
    Õ
    0.81
    íķ
    0.79
    Availability
    0.75
     darn
    0.72
    WHERE
    0.69
     anymore
    0.68
    ãģĦ
    0.67
    gets
    0.66
     bothered
    0.66
     godd
    0.65
    Activations Density 0.077%

    No Known Activations