© 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. 19650
    Prev
    Next
    INDEX
    Explanations

    references to rules and regulations

    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
    708
    +0.10
    0.5%
    598
    +0.10
    0.4%
    386
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    708
    +0.10
    0.02
    598
    +0.10
    0.01
    386
    +0.09
    0.02
    Negative Logits
    itate
    -0.92
     Hots
    -0.83
    ité
    -0.82
    acters
    -0.82
    ity
    -0.76
    itant
    -0.73
    velength
    -0.73
    ãĥ¤
    -0.72
    assador
    -0.69
    SIGN
    -0.67
    POSITIVE LOGITS
    book
    1.32
    books
    1.21
    making
    1.11
    breaker
    0.99
    breakers
    0.96
    makers
    0.94
    maker
    0.93
    breaking
    0.90
    lessness
    0.85
    BOOK
    0.83
    Activations Density 0.016%

    No Known Activations