© 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. 17085
    Prev
    Next
    INDEX
    Explanations

    examples of repeated occurrences

    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
    718
    +0.14
    0.6%
    218
    +0.10
    0.4%
    757
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.14
    0.04
    133
    +0.10
    0.03
    757
    +0.09
    0.03
    Negative Logits
    rend
    -0.90
    aim
    -0.81
    unity
    -0.71
    scribe
    -0.71
    hammad
    -0.69
    cel
    -0.67
    Exit
    -0.66
    asy
    -0.65
    cent
    -0.65
    main
    -0.64
    POSITIVE LOGITS
     remotely
    0.94
    handedly
    0.92
     though
    0.89
     tho
    0.88
     joked
    0.83
     hinted
    0.79
    handed
    0.78
     entertained
    0.74
     briefly
    0.74
     resorted
    0.73
    Activations Density 0.050%

    No Known Activations