© 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. 19710
    Prev
    Next
    INDEX
    Explanations

    contact information and web links

    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
    373
    +0.12
    0.5%
    766
    +0.10
    0.5%
    407
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.03
    409
    +0.10
    0.03
    766
    +0.09
    0.02
    Negative Logits
     Jungle
    -0.90
     Moonlight
    -0.75
     revenge
    -0.75
     selfies
    -0.69
     Sour
    -0.69
     vengeance
    -0.66
     Diesel
    -0.66
     Cinderella
    -0.66
     shaving
    -0.64
     Ghost
    -0.63
    POSITIVE LOGITS
    gov
    1.41
    edu
    1.31
    ucl
    1.14
    org
    1.05
    uckland
    0.95
    ournals
    0.93
    central
    0.92
    western
    0.91
    debian
    0.87
    microsoft
    0.87
    Activations Density 0.046%

    No Known Activations