© 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. 10959
    Prev
    Next
    INDEX
    Explanations

    words related to an individual's name or username

    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
    537
    +0.10
    0.4%
    274
    +0.09
    0.4%
    503
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.02
    284
    +0.09
    0.02
    588
    +0.09
    0.01
    Negative Logits
    esville
    -0.83
    creen
    -0.81
    eph
    -0.71
    ĺħ
    -0.69
    vention
    -0.66
    ciating
    -0.66
    fixed
    -0.64
    erness
    -0.63
    ±
    -0.63
    etimes
    -0.63
    POSITIVE LOGITS
    antly
    1.07
    atically
    1.04
    untled
    1.01
    rr
    0.99
    ange
    0.98
    idge
    0.94
    aciously
    0.91
    abbit
    0.91
    ands
    0.89
    acious
    0.88
    Activations Density 0.037%

    No Known Activations