© 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. 20432
    Prev
    Next
    INDEX
    Explanations

    keywords related to information technology and software development processes

    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
    739
    +0.12
    0.6%
    393
    +0.10
    0.5%
    484
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.12
    0.05
    0
    +0.10
    0.05
    393
    +0.09
    0.05
    Negative Logits
    meet
    -0.80
    existence
    -0.72
    ibl
    -0.71
    arth
    -0.71
    bler
    -0.71
    nces
    -0.70
    ANC
    -0.69
    DEN
    -0.69
    lance
    -0.69
    iors
    -0.68
    POSITIVE LOGITS
     THEN
    1.11
     then
    1.07
     proceeded
    1.03
     shove
    0.98
     toss
    0.94
     threw
    0.93
     put
    0.88
     assign
    0.87
     vo
    0.85
     thence
    0.84
    Activations Density 0.276%

    No Known Activations