© 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. 18947
    Prev
    Next
    INDEX
    Explanations

    phrases related to job contracts and commitments

    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
    616
    +0.12
    0.6%
    218
    +0.11
    0.5%
    100
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.12
    0.05
    100
    +0.11
    0.04
    748
    +0.09
    0.03
    Negative Logits
    auga
    -0.78
    ument
    -0.74
    `
    -0.64
    ospace
    -0.63
    okia
    -0.63
     Begins
    -0.61
    bernatorial
    -0.60
    Opening
    -0.60
    \-
    -0.59
    istical
    -0.59
    POSITIVE LOGITS
    dogs
    1.07
    cuts
    1.05
    lines
    1.04
    pins
    1.02
    neath
    1.01
    lining
    0.98
    whelming
    0.96
    cutting
    0.94
    pants
    0.94
    lie
    0.93
    Activations Density 0.043%

    No Known Activations