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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 43350
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals or groups in sports and politics

    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
    120
    +0.10
    0.5%
    311
    +0.10
    0.4%
    718
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.10
    0.01
    335
    +0.10
    0.00
    485
    +0.09
    0.00
    Negative Logits
    matically
    -0.86
    perse
    -0.82
    ingham
    -0.81
    pled
    -0.80
    İĭ
    -0.80
    plain
    -0.80
    mable
    -0.79
    mes
    -0.78
    brance
    -0.75
    rums
    -0.74
    POSITIVE LOGITS
    icio
    0.91
     Poc
    0.87
     Rican
    0.78
    chi
    0.76
     Sul
    0.75
    inho
    0.74
     Fernandez
    0.70
     Antonio
    0.68
     Aires
    0.67
     Powers
    0.67
    Activations Density 0.003%

    No Known Activations