© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26581
    Prev
    Next
    INDEX
    Explanations

    terms related to specific national or cultural identities

    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
    394
    +0.11
    0.5%
    752
    +0.10
    0.5%
    126
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.11
    0.04
    288
    +0.10
    0.03
    267
    +0.08
    0.03
    Negative Logits
    alus
    -0.77
    utterstock
    -0.73
    trap
    -0.69
    USS
    -0.69
    htaking
    -0.68
    oÄŁan
    -0.68
    erella
    -0.66
    Downloadha
    -0.65
    é¾įå¥ij士
    -0.64
     Bayer
    -0.63
    POSITIVE LOGITS
     Association
    0.92
     Conference
    0.90
     Partnership
    0.89
     Alliance
    0.82
     Improvement
    0.79
     Distribut
    0.79
     Regiment
    0.76
     Convention
    0.76
     Survey
    0.74
     Organization
    0.74
    Activations Density 0.062%

    No Known Activations