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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13686
    Prev
    Next
    INDEX
    Explanations

    same three-letter name with a number at the end

    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
    232
    +0.14
    0.6%
    187
    +0.10
    0.4%
    62
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.02
    141
    +0.10
    0.01
    699
    +0.09
    0.01
    Negative Logits
    ktop
    -0.72
     versa
    -0.69
     derog
    -0.68
     wiret
    -0.65
     condol
    -0.62
     empowered
    -0.62
     spect
    -0.61
     referen
    -0.60
     relativity
    -0.60
     presidents
    -0.60
    POSITIVE LOGITS
    shaw
    1.33
    enton
    1.22
    ford
    1.17
     Pitt
    0.99
    bury
    0.93
    street
    0.93
    rill
    0.86
    mund
    0.84
    ilda
    0.84
    ney
    0.82
    Activations Density 0.014%

    No Known Activations