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. 25561
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and disputes

    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
    480
    +0.52
    2.9%
    362
    +0.19
    1.1%
    393
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.52
    0.17
    608
    +0.19
    0.13
    385
    +0.17
    0.12
    Negative Logits
     furthermore
    -0.71
     besides
    -0.69
     beforehand
    -0.67
     namely
    -0.67
     accordingly
    -0.66
     depended
    -0.66
    !.
    -0.66
     afterwards
    -0.65
    *.
    -0.64
     thereafter
    -0.62
    POSITIVE LOGITS
     latest
    0.97
     Dalai
    0.90
    resa
    0.90
     Philippines
    0.90
     nation
    0.90
     United
    0.89
     deadliest
    0.88
     largest
    0.87
     Clintons
    0.84
     Kremlin
    0.83
    Activations Density 0.693%

    No Known Activations