© 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. 23962
    Prev
    Next
    INDEX
    Explanations

    articles and quantifiers indicating selection or choices

    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
    109
    +0.12
    0.5%
    637
    +0.12
    0.5%
    717
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    717
    +0.12
    0.03
    276
    +0.12
    0.03
    36
    +0.10
    0.03
    Negative Logits
    ĸļ
    -1.10
    behind
    -0.81
    mediated
    -0.81
    visible
    -0.81
    cule
    -0.81
    ei
    -0.78
    Requires
    -0.77
    naissance
    -0.76
    cular
    -0.74
    ngth
    -0.73
    POSITIVE LOGITS
     appropriate
    0.87
     preferred
    0.84
     preset
    0.84
     winners
    0.84
     successor
    0.84
     winner
    0.84
     suitable
    0.84
     destination
    0.83
     finalists
    0.81
     direction
    0.79
    Activations Density 0.075%

    No Known Activations