© 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. 2886
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Sk" with different numbers next to them

    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
    659
    +0.14
    0.6%
    575
    +0.12
    0.6%
    232
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.03
    232
    +0.12
    0.03
    204
    +0.12
    0.02
    Negative Logits
     slee
    -0.67
     Mayweather
    -0.66
     joy
    -0.64
     writ
    -0.64
     sanity
    -0.63
     palpable
    -0.63
    Reloaded
    -0.61
     ridiculous
    -0.59
     belt
    -0.59
     loose
    -0.59
    POSITIVE LOGITS
    yrim
    1.33
    ipper
    1.33
    ull
    1.24
    ysc
    1.22
    oln
    1.18
    ratch
    1.17
    ippers
    1.15
    irts
    1.13
    aven
    1.10
    imming
    1.08
    Activations Density 0.017%

    No Known Activations