© 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. 24565
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to significant events or performances

    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
    355
    +0.14
    0.6%
    545
    +0.09
    0.4%
    735
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.14
    0.04
    693
    +0.09
    0.04
    223
    +0.09
    0.04
    Negative Logits
     downside
    -0.68
     Collider
    -0.66
     ledge
    -0.62
     couch
    -0.61
     label
    -0.59
     promise
    -0.59
     privilege
    -0.57
     menace
    -0.57
     stigma
    -0.56
     negotiators
    -0.56
    POSITIVE LOGITS
     increments
    0.98
     places
    0.94
     installments
    0.91
     minutes
    0.90
     consecutive
    0.84
     directions
    0.84
     months
    0.83
     weeks
    0.83
     quarters
    0.83
     contexts
    0.82
    Activations Density 0.083%

    No Known Activations