© 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. 9055
    Prev
    Next
    INDEX
    Explanations

    text related to technical instructions

    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
    393
    +0.14
    0.6%
    159
    +0.13
    0.6%
    640
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.14
    0.08
    186
    +0.13
    0.05
    767
    +0.10
    0.05
    Negative Logits
    onto
    -0.87
    agi
    -0.72
    ignt
    -0.71
    ials
    -0.69
    adle
    -0.68
    KNOWN
    -0.68
    ickets
    -0.67
    ãĤ¨ãĥ«
    -0.66
    stones
    -0.66
    omo
    -0.66
    POSITIVE LOGITS
     week
    1.09
     article
    1.08
     slideshow
    0.99
     month
    0.93
     excerpt
    0.88
     concludes
    0.86
     Week
    0.86
     weekend
    0.86
     year
    0.86
     transcript
    0.85
    Activations Density 0.135%

    No Known Activations