© 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. 37300
    Prev
    Next
    INDEX
    Explanations

    the term "Best" in various contexts related to rankings or evaluations

    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
    128
    +0.11
    0.5%
    339
    +0.11
    0.5%
    654
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.11
    0.02
    128
    +0.11
    0.02
    276
    +0.10
    0.02
    Negative Logits
    IGHTS
    -0.74
    gypt
    -0.73
    heter
    -0.70
     probing
    -0.69
    chy
    -0.67
    mble
    -0.64
    vor
    -0.63
    bryce
    -0.62
    pher
    -0.61
    gy
    -0.61
    POSITIVE LOGITS
    iary
    1.14
    seller
    1.13
    iaries
    1.04
     Practices
    0.93
    sell
    0.89
    selling
    0.86
     Selling
    0.85
    ow
    0.81
     Friend
    0.78
    owing
    0.78
    Activations Density 0.021%

    No Known Activations