© 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 49152
    9. 8-RES_FS49152-JB
    11. 37234
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.13
    0.6%
    640
    +0.12
    0.6%
    2
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.13
    0.03
    362
    +0.12
    0.03
    250
    +0.10
    0.02
    Negative Logits
     accounted
    -0.66
    igue
    -0.64
    Joined
    -0.64
    fuck
    -0.63
     behaves
    -0.63
     ancest
    -0.63
     portrayal
    -0.61
    boxing
    -0.60
    wrong
    -0.59
     thereof
    -0.57
    POSITIVE LOGITS
    interstitial
    0.71
     these
    0.70
     the
    0.68
     this
    0.67
     Anthem
    0.63
    nesday
    0.63
    eatures
    0.63
     Dawn
    0.63
     our
    0.62
     Reloaded
    0.62
    Activations Density 0.067%

    No Known Activations