Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1091
    Prev
    Next
    INDEX
    Explanations

    words related to color

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    459
    +0.10
    0.4%
    634
    +0.10
    0.4%
    109
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.10
    0.03
    459
    +0.10
    0.03
    392
    +0.09
    0.03
    Negative Logits
    doms
    -1.10
    _-
    -0.88
    uthor
    -0.85
    olicy
    -0.82
    idem
    -0.80
    ernel
    -0.72
    rolet
    -0.70
     Cheong
    -0.70
    ancock
    -0.69
    uckland
    -0.69
    POSITIVE LOGITS
     palette
    1.15
    blind
    1.13
     tint
    0.93
     coded
    0.92
    anguage
    0.90
     hue
    0.88
    ="#
    0.88
     dye
    0.85
     color
    0.85
     Spray
    0.84
    Activations Density 0.087%

    No Known Activations