© 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. 19903
    Prev
    Next
    INDEX
    Explanations

    information related to news stories or events

    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
    314
    +0.14
    0.6%
    732
    +0.10
    0.4%
    694
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.14
    0.04
    693
    +0.10
    0.05
    412
    +0.09
    0.03
    Negative Logits
     captcha
    -0.77
     legions
    -0.65
     hurts
    -0.65
     cures
    -0.63
    oiler
    -0.62
    xit
    -0.62
     recourse
    -0.61
     reveals
    -0.60
    ãĥ¯
    -0.60
     mouths
    -0.58
    POSITIVE LOGITS
    terday
    0.84
    livious
    0.73
     earlier
    0.68
     asleep
    0.67
    uties
    0.66
    angering
    0.66
     chatting
    0.65
    employed
    0.65
     yesterday
    0.64
     Wanted
    0.64
    Activations Density 0.619%

    No Known Activations