© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 49152
    9. 8-RES_FS49152-JB
    11. 26846
    Prev
    Next
    INDEX
    Explanations

    topics related to healthcare and religious institutions' influence on social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    480
    +0.33
    1.6%
    373
    +0.15
    0.7%
    57
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.33
    0.10
    57
    +0.15
    0.05
    537
    +0.12
    0.05
    Negative Logits
    é¾įåĸļ士
    -0.73
    ãĤ¨ãĥ«
    -0.67
    iannopoulos
    -0.62
    hene
    -0.58
    sem
    -0.56
    irth
    -0.54
    forth
    -0.54
    unin
    -0.53
    cule
    -0.53
    ledged
    -0.52
    POSITIVE LOGITS
    /
    0.59
    cellaneous
    0.59
    /
    0.57
    .--
    0.56
    !:
    0.56
     and
    0.55
    IRC
    0.55
     meanwhile
    0.55
     or
    0.55
    /_
    0.54
    Activations Density 0.610%

    No Known Activations