© 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. 12137
    Prev
    Next
    INDEX
    Explanations

    personal experiences and stories shared in interviews

    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
    378
    +0.14
    0.6%
    565
    +0.10
    0.5%
    303
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    697
    +0.14
    0.03
    8
    +0.10
    0.04
    119
    +0.09
    0.03
    Negative Logits
    '."
    -0.79
     Sinclair
    -0.68
     Pai
    -0.65
    .'"
    -0.65
    pered
    -0.62
    ]."
    -0.61
     Pelosi
    -0.60
    arted
    -0.59
    insert
    -0.59
     Dems
    -0.59
    POSITIVE LOGITS
     definitely
    0.97
    initely
    0.96
     answer
    0.89
    laughs
    0.88
     certainly
    0.85
     depends
    0.81
    Laughs
    0.80
     anecd
    0.80
     yeah
    0.79
    Absolutely
    0.79
    Activations Density 0.306%

    No Known Activations