© 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. 22454
    Prev
    Next
    INDEX
    Explanations

    variations of the word "aver."

    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
    120
    +0.13
    0.6%
    128
    +0.11
    0.5%
    465
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.01
    120
    +0.11
    0.01
    284
    +0.10
    0.01
    Negative Logits
    undo
    -0.78
    fixes
    -0.71
    eln
    -0.68
    estinal
    -0.66
     relativity
    -0.64
    orem
    -0.63
    oret
    -0.61
    esthesia
    -0.61
    emonic
    -0.60
     Fundamental
    -0.59
    POSITIVE LOGITS
    vier
    1.03
    ionage
    1.01
    ider
    0.89
    TAIN
    0.84
    baum
    0.82
    kus
    0.79
    lust
    0.75
    igion
    0.75
    iour
    0.74
    idge
    0.73
    Activations Density 0.024%

    No Known Activations