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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 41386
    Prev
    Next
    INDEX
    Explanations

    references to Osama bin Laden

    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
    288
    +0.12
    0.6%
    762
    +0.12
    0.5%
    711
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.12
    0.01
    711
    +0.12
    0.01
    494
    +0.11
    0.01
    Negative Logits
    aic
    -0.72
     antioxid
    -0.70
    Brew
    -0.70
    Ott
    -0.68
     Constantin
    -0.67
     Celt
    -0.67
    Lex
    -0.67
     Cullen
    -0.66
    Balt
    -0.66
    Rate
    -0.66
    POSITIVE LOGITS
     Laden
    0.95
     himself
    0.93
     Hussein
    0.91
    addafi
    0.85
    ensis
    0.85
    abad
    0.84
     Jinping
    0.83
     assassinated
    0.82
    istani
    0.81
     terrorists
    0.75
    Activations Density 0.011%

    No Known Activations