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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23388
    Prev
    Next
    INDEX
    Explanations

    references to firearms and weapons

    oai_token-act-pair · gpt-4o-miniTriggered 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
    343
    +0.14
    0.6%
    288
    +0.11
    0.5%
    346
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.14
    0.03
    258
    +0.11
    0.03
    516
    +0.10
    0.03
    Negative Logits
    gres
    -0.80
     Publisher
    -0.73
    grad
    -0.71
     Hort
    -0.70
    DAY
    -0.69
    IONS
    -0.68
    rosso
    -0.68
     Clouds
    -0.67
     Strawberry
    -0.66
     Archdemon
    -0.64
    POSITIVE LOGITS
    powder
    1.30
    linger
    1.07
     guns
    1.04
     handguns
    1.01
     ammunition
    1.01
     confiscated
    0.99
     firearms
    0.98
     pistols
    0.97
     holster
    0.96
     muzzle
    0.96
    Activations Density 0.039%

    No Known Activations