© 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. 7170
    Prev
    Next
    INDEX
    Explanations

    details about events, schedules, and programs, especially related to politics, sports, and media

    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
    589
    +0.10
    0.5%
    394
    +0.10
    0.5%
    721
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    296
    +0.10
    0.05
    460
    +0.10
    0.04
    495
    +0.09
    0.04
    Negative Logits
     behav
    -0.61
     inspectors
    -0.58
    izations
    -0.58
     orderly
    -0.57
     dearly
    -0.56
     dossier
    -0.56
     collaborations
    -0.55
    ERY
    -0.55
    izoph
    -0.53
     improvements
    -0.53
    POSITIVE LOGITS
     apiece
    1.04
     intervals
    0.84
     sidx
    0.75
    point
    0.73
    pm
    0.71
    uca
    0.71
    cand
    0.71
     PDT
    0.70
     magnification
    0.69
     wavelengths
    0.69
    Activations Density 0.158%

    No Known Activations