© 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. 21087
    Prev
    Next
    INDEX
    Explanations

    dates in the format (Month Year) where the year is 2010 or later

    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
    373
    +0.16
    0.8%
    570
    +0.09
    0.4%
    241
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.16
    0.04
    176
    +0.09
    0.03
    373
    +0.09
    -0.02
    Negative Logits
    Reviewer
    -0.72
     pseudonym
    -0.57
    judicial
    -0.57
     merits
    -0.56
     Sas
    -0.56
     recl
    -0.54
     prosecut
    -0.54
     reconc
    -0.53
     authorizing
    -0.53
     exposition
    -0.52
    POSITIVE LOGITS
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    0.86
    âĶĢâĶĢâĶĢâĶĢ
    0.86
     ..............
    0.83
    OTAL
    0.82
     ----------------
    0.80
    ¼
    0.77
     âľĶ
    0.76
     ???
    0.74
    ________
    0.69
    ................................
    0.69
    Activations Density 0.216%

    No Known Activations