© 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. 19693
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people, sports teams, and events within news articles

    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
    447
    +0.31
    1.6%
    480
    +0.28
    1.4%
    481
    +0.22
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.31
    0.10
    461
    +0.28
    0.07
    288
    +0.22
    0.10
    Negative Logits
    ãģĻ
    -0.65
    $.
    -0.63
     thereof
    -0.57
     ..."
    -0.56
     guiActiveUnfocused
    -0.55
    Redd
    -0.53
    ãĤ¤ãĥĪ
    -0.52
    Eva
    -0.52
    }.
    -0.52
     requisite
    -0.52
    POSITIVE LOGITS
     meanwhile
    1.10
     reacted
    0.88
     responded
    0.83
     fared
    0.82
     declined
    0.79
     spokesman
    0.75
     reportedly
    0.74
     also
    0.74
     awoke
    0.74
     grew
    0.74
    Activations Density 0.887%

    No Known Activations