© 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. 26505
    Prev
    Next
    INDEX
    Explanations

    codes or model numbers for various products and items

    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
    447
    +0.14
    0.7%
    524
    +0.11
    0.5%
    388
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.14
    0.03
    343
    +0.11
    0.03
    326
    +0.10
    0.02
    Negative Logits
     margins
    -0.70
    \\\\\\\\
    -0.67
    isman
    -0.65
     snowball
    -0.63
     lawy
    -0.63
    ogene
    -0.62
     Fior
    -0.60
     profitable
    -0.60
    âĸ¬
    -0.58
    iciary
    -0.58
    POSITIVE LOGITS
    00
    1.00
    01
    0.99
    DM
    0.97
    017
    0.94
    50
    0.93
    XX
    0.93
    eus
    0.91
    014
    0.90
    005
    0.90
    70
    0.90
    Activations Density 0.042%

    No Known Activations