© 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 24576
    9. 8-RES_FS24576-JB
    11. 1763
    Prev
    Next
    INDEX
    Explanations

    texts related to professional commitment and dedication

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    87
    +0.20
    1.0%
    102
    +0.11
    0.5%
    567
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.20
    0.09
    718
    +0.11
    0.07
    566
    +0.10
    0.05
    Negative Logits
    idav
    -0.63
     Pwr
    -0.61
     PHOTO
    -0.61
     recalls
    -0.61
     partName
    -0.56
     reminds
    -0.56
    cellaneous
    -0.56
     quotes
    -0.55
    pedia
    -0.55
     Cheong
    -0.54
    POSITIVE LOGITS
     worthwhile
    0.75
     indeed
    0.73
    acea
    0.71
     fundamentally
    0.71
    better
    0.70
     viable
    0.70
     unacceptable
    0.69
     achievable
    0.67
     sufficiently
    0.66
     truly
    0.66
    Activations Density 0.867%

    No Known Activations