© 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. 22461
    Prev
    Next
    INDEX
    Explanations

    statistical performance metrics and averages of players in baseball

    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
    538
    +0.09
    0.4%
    413
    +0.09
    0.4%
    467
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.09
    0.02
    326
    +0.09
    0.01
    316
    +0.08
    0.01
    Negative Logits
    arya
    -0.89
    ayers
    -0.70
    orks
    -0.70
    quest
    -0.68
    hai
    -0.66
    foreseen
    -0.65
    netflix
    -0.65
    changes
    -0.65
    ophob
    -0.65
    anol
    -0.63
    POSITIVE LOGITS
    /.
    1.15
    -.
    0.95
     hitter
    0.91
     batting
    0.90
     avg
    0.79
     halftime
    0.76
    (-
    0.74
     homer
    0.71
    /+
    0.71
    Percent
    0.69
    Activations Density 0.031%

    No Known Activations