© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22675
    Prev
    Next
    INDEX
    Explanations

    names of Indian surfers and related competitive events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    58
    +0.12
    0.5%
    447
    +0.11
    0.5%
    544
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.12
    0.03
    288
    +0.11
    0.04
    467
    +0.11
    0.02
    Negative Logits
    Rated
    -1.02
    instead
    -0.68
     ______
    -0.66
    çİĭ
    -0.66
    ãĥ´ãĤ¡
    -0.63
    Medium
    -0.61
    ãĤ¤ãĥĪ
    -0.61
    geist
    -0.61
    ITH
    -0.60
    VALUE
    -0.59
    POSITIVE LOGITS
     caveats
    0.67
     aforementioned
    0.65
     cameo
    0.63
     exceptions
    0.63
     itself
    0.61
     nods
    0.60
     surprises
    0.58
     fiasco
    0.58
     disclaimer
    0.58
     medals
    0.57
    Activations Density 0.268%

    No Known Activations