© 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. 1
    Prev
    Next
    INDEX
    Explanations

    mentions of dates and specific times

    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
    36
    +0.19
    0.9%
    373
    +0.11
    0.5%
    238
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.19
    0.04
    448
    +0.11
    0.02
    319
    +0.09
    0.02
    Negative Logits
     Annotations
    -0.61
    ahime
    -0.61
    Aid
    -0.60
     AGA
    -0.58
     Agent
    -0.58
     unseen
    -0.58
     comparisons
    -0.57
     Inher
    -0.56
     affection
    -0.56
    raltar
    -0.56
    POSITIVE LOGITS
     week
    0.89
    clock
    0.88
     month
    0.81
     weekday
    0.80
    pm
    0.78
    ught
    0.78
     midnight
    0.77
     cycle
    0.77
    iren
    0.76
     curfew
    0.75
    Activations Density 0.028%

    No Known Activations