© 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 24576
    9. 8-RES_FS24576-JB
    11. 11014
    Prev
    Next
    INDEX
    Explanations

    terms related to power dynamics or performances

    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
    755
    +0.10
    0.5%
    288
    +0.10
    0.4%
    160
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.10
    0.03
    755
    +0.10
    0.03
    259
    +0.09
    0.03
    Negative Logits
    romeda
    -0.72
     Niet
    -0.68
    roit
    -0.67
    eret
    -0.67
     Bei
    -0.67
    OOL
    -0.67
    eryl
    -0.65
    algia
    -0.64
     Von
    -0.63
    olson
    -0.63
    POSITIVE LOGITS
    houses
    1.05
    stroke
    1.03
    lifting
    0.97
     outage
    0.90
    puff
    0.89
    train
    0.85
    lessness
    0.82
    full
    0.80
     chords
    0.80
    Reviewer
    0.80
    Activations Density 0.035%

    No Known Activations