© 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. 37237
    Prev
    Next
    INDEX
    Explanations

    terms indicating inability or lack of certainty

    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
    199
    +0.11
    0.5%
    744
    +0.10
    0.4%
    232
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    199
    +0.11
    0.01
    616
    +0.10
    0.01
    744
    +0.09
    0.01
    Negative Logits
     roofs
    -0.69
     rooftop
    -0.69
     heights
    -0.67
    unks
    -0.64
     Telephone
    -0.63
     Elves
    -0.62
     rooft
    -0.62
    AFTA
    -0.61
    Interstitial
    -0.61
     nickname
    -0.61
    POSITIVE LOGITS
    haust
    1.32
    cus
    1.17
    orable
    1.13
    uably
    1.10
    press
    1.10
    pert
    1.05
    actly
    1.04
    ensibly
    1.02
    ordinary
    1.02
    cient
    1.01
    Activations Density 0.004%

    No Known Activations