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 49152
    5. 8-RES_FS49152-JB
    6. 43303
    Prev
    Next
    INDEX
    Explanations

    mentions of anything related to Japan or Japanese culture

    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
    272
    +0.10
    0.5%
    173
    +0.10
    0.4%
    57
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    342
    +0.10
    0.02
    57
    +0.10
    0.02
    173
    +0.09
    0.02
    Negative Logits
    vable
    -0.89
    rent
    -0.87
    riers
    -0.86
    lier
    -0.80
    ttes
    -0.79
    izons
    -0.78
    staking
    -0.77
     BET
    -0.76
    thumbnails
    -0.76
    ully
    -0.75
    POSITIVE LOGITS
     Yen
    1.18
     yen
    1.07
    £ı
    0.85
    oka
    0.81
     nationals
    0.78
    imura
    0.78
    apolis
    0.73
     Imperial
    0.73
     Meteor
    0.71
     Airlines
    0.71
    Activations Density 0.009%

    No Known Activations