© 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. 22394
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.19
    0.9%
    481
    +0.16
    0.7%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    595
    +0.19
    0.05
    393
    +0.16
    0.05
    714
    +0.10
    0.04
    Negative Logits
    rb
    -0.82
    omic
    -0.70
    opa
    -0.68
    oused
    -0.67
    abul
    -0.67
    hower
    -0.66
    fell
    -0.66
    ÃŃs
    -0.65
    umar
    -0.65
    ":{"
    -0.65
    POSITIVE LOGITS
     assorted
    1.19
     etc
    1.09
    etc
    1.01
     finally
    0.93
     blah
    0.91
     downright
    0.80
     possibly
    0.79
     ect
    0.74
     vo
    0.73
     ultimately
    0.71
    Activations Density 0.218%

    No Known Activations