© 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. 19634
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology, entertainment, and events happening in a work or fictional setting

    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
    87
    +0.23
    1.2%
    459
    +0.10
    0.5%
    464
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.23
    0.08
    224
    +0.10
    0.08
    700
    +0.10
    0.07
    Negative Logits
    margin
    -0.58
    rising
    -0.56
    "?
    -0.56
    foundland
    -0.55
    %:
    -0.54
     Related
    -0.53
    unless
    -0.51
     Canaver
    -0.50
    rely
    -0.50
     TOTAL
    -0.49
    POSITIVE LOGITS
     intervened
    0.95
     gave
    0.86
     blew
    0.85
     opted
    0.84
     took
    0.83
     deems
    0.78
     couldn
    0.78
     went
    0.78
     withdrew
    0.78
     showed
    0.77
    Activations Density 0.612%

    No Known Activations