© 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. 12071
    Prev
    Next
    INDEX
    Explanations

    references to specific actions or events, especially those that require investigation or review

    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
    481
    +0.14
    0.6%
    393
    +0.14
    0.6%
    329
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.04
    611
    +0.14
    0.04
    97
    +0.11
    0.03
    Negative Logits
    oult
    -0.62
    ring
    -0.62
    ringe
    -0.61
    cil
    -0.60
    Catalog
    -0.60
    twitch
    -0.60
    ulla
    -0.59
     Toro
    -0.59
    igue
    -0.59
    Thumbnail
    -0.59
    POSITIVE LOGITS
     sorts
    0.90
     course
    0.76
     the
    0.73
     these
    0.70
     existing
    0.70
     literature
    0.66
    Ĭ±
    0.65
     their
    0.65
     each
    0.65
     its
    0.64
    Activations Density 0.159%

    No Known Activations