Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 40072
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the significance or implications of events or actions

    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
    718
    +0.12
    0.6%
    688
    +0.11
    0.5%
    388
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    688
    +0.12
    0.03
    239
    +0.11
    0.02
    718
    +0.11
    0.03
    Negative Logits
    @#&
    -0.86
    atech
    -0.81
    iazep
    -0.77
    oqu
    -0.67
    opsis
    -0.67
    phrine
    -0.66
    thumbnails
    -0.66
    uded
    -0.65
    otrop
    -0.64
    imate
    -0.64
    POSITIVE LOGITS
     goodbye
    1.08
     sacrificing
    0.93
     abandoning
    0.85
     risking
    0.82
    LOS
    0.81
     nothing
    0.80
     something
    0.74
     fewer
    0.73
     avoiding
    0.72
     losing
    0.68
    Activations Density 0.028%

    No Known Activations