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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19425
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific phrases related to political figures and 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
    393
    +0.15
    0.7%
    640
    +0.10
    0.5%
    509
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.04
    393
    +0.10
    0.04
    448
    +0.09
    0.02
    Negative Logits
    warts
    -0.72
    ancock
    -0.69
    iatus
    -0.68
    ukemia
    -0.67
    ufact
    -0.66
    odiac
    -0.66
    inois
    -0.64
    zon
    -0.63
    leneck
    -0.62
    tackle
    -0.61
    POSITIVE LOGITS
     same
    1.02
     hashtag
    1.00
     restroom
    0.95
     phrase
    0.90
     pseudonym
    0.89
     opportunity
    0.89
     excuse
    0.88
     analogy
    0.86
     tactic
    0.84
     technique
    0.84
    Activations Density 0.115%

    No Known Activations