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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7389
    Prev
    Next
    INDEX
    Explanations

    references to a specific chemical compound or class name starting with 'bor'

    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
    742
    +0.11
    0.5%
    624
    +0.11
    0.5%
    496
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.01
    326
    +0.11
    0.01
    288
    +0.10
    0.02
    Negative Logits
    HER
    -0.82
    cius
    -0.74
    eah
    -0.72
    apo
    -0.70
    pta
    -0.69
    erate
    -0.66
    éĹĺ
    -0.64
    eters
    -0.63
    cers
    -0.62
     honor
    -0.61
    POSITIVE LOGITS
    rowing
    1.05
    rower
    0.92
    hood
    0.83
    ing
    0.81
    rows
    0.79
    bid
    0.78
    ODY
    0.77
    rough
    0.74
    wood
    0.72
    rigan
    0.71
    Activations Density 0.034%

    No Known Activations