© 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. 23993
    Prev
    Next
    INDEX
    Explanations

    questions and concepts related to age, type, reason, and difficulty

    oai_token-act-pair · gpt-4o-miniTriggered 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
    463
    +0.15
    0.7%
    311
    +0.10
    0.4%
    57
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.15
    0.04
    449
    +0.10
    0.03
    60
    +0.10
    0.03
    Negative Logits
    hig
    -0.78
    iHUD
    -0.72
    Interstitial
    -0.71
    hover
    -0.68
    $.
    -0.67
    %);
    -0.64
    ilan
    -0.64
    $,
    -0.61
    FAULT
    -0.60
    essage
    -0.59
    POSITIVE LOGITS
    ?
    1.63
    ?"
    1.50
    ?!
    1.50
    ?:
    1.50
    ?)
    1.48
    ?'
    1.42
    ?),
    1.41
    ?!"
    1.40
    !?
    1.40
    ?]
    1.39
    Activations Density 0.095%

    No Known Activations