© 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. 37384
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating lists or connections

    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
    104
    +0.11
    0.5%
    214
    +0.09
    0.4%
    46
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.11
    0.03
    398
    +0.09
    0.04
    284
    +0.09
    0.03
    Negative Logits
    cens
    -0.86
     Latvia
    -0.64
    birth
    -0.63
    earable
    -0.62
    juven
    -0.62
    ibly
    -0.61
    UGH
    -0.61
     Journalism
    -0.61
    readable
    -0.60
    idation
    -0.59
    POSITIVE LOGITS
     bolts
    0.68
     Testament
    0.67
     cure
    0.66
     remedies
    0.65
     symptoms
    0.63
     potatoes
    0.62
     Conditions
    0.62
     suffix
    0.61
     condition
    0.60
     parcel
    0.60
    Activations Density 0.103%

    No Known Activations