© 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. 37039
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" in various contexts

    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
    579
    +0.11
    0.5%
    541
    +0.10
    0.5%
    273
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    579
    +0.11
    0.01
    111
    +0.10
    0.01
    284
    +0.10
    0.01
    Negative Logits
     outl
    -0.78
    ividual
    -0.74
    mble
    -0.70
     averages
    -0.65
    raising
    -0.64
     appropri
    -0.63
     oun
    -0.63
     vein
    -0.63
     working
    -0.63
    ancies
    -0.61
    POSITIVE LOGITS
    ilet
    1.11
    jo
    1.04
    ppo
    1.03
    fen
    1.00
    pper
    0.93
    ppa
    0.93
    pping
    0.93
    fore
    0.92
    ffee
    0.91
    ven
    0.91
    Activations Density 0.007%

    No Known Activations