© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 37246
    Prev
    Next
    INDEX
    Explanations

    mentions and references to news organizations and media entities

    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
    314
    +0.10
    0.4%
    643
    +0.10
    0.4%
    497
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.10
    0.03
    508
    +0.10
    0.02
    314
    +0.09
    0.00
    Negative Logits
    naire
    -0.77
    olation
    -0.68
     vis
    -0.66
     ported
    -0.63
    lyak
    -0.62
     gorilla
    -0.62
    naires
    -0.62
     ¶
    -0.61
     Faust
    -0.61
     stomp
    -0.60
    POSITIVE LOGITS
    News
    1.08
    iframe
    0.95
    Subscribe
    0.95
    news
    0.94
    Politics
    0.92
    bleacher
    0.91
    Daily
    0.89
    Magazine
    0.87
    Week
    0.86
    Sports
    0.86
    Activations Density 0.067%

    No Known Activations