© 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 EvalsExportsAPI 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. 12287
    Prev
    Next
    INDEX
    Explanations

    details or information related to technical coding processes

    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
    261
    +0.11
    0.5%
    83
    +0.10
    0.5%
    292
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.03
    373
    +0.10
    -0.01
    284
    +0.10
    0.03
    Negative Logits
     allegiance
    -0.72
     pestic
    -0.71
     Airl
    -0.70
    PRES
    -0.69
    enegger
    -0.63
    chwitz
    -0.63
     enthusi
    -0.62
    Revolution
    -0.61
     extermination
    -0.60
    TEXTURE
    -0.58
    POSITIVE LOGITS
    ishable
    0.68
    handled
    0.66
    zee
    0.63
    meal
    0.63
    poons
    0.63
    ished
    0.61
    organic
    0.59
    oppy
    0.59
    inarily
    0.59
    igans
    0.58
    Activations Density 0.094%

    No Known Activations