© 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. 11083
    Prev
    Next
    INDEX
    Explanations

    dates in the format "YYYY" that appear in the text

    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
    146
    +0.14
    0.6%
    339
    +0.12
    0.5%
    496
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.14
    0.03
    306
    +0.12
    0.02
    24
    +0.11
    0.02
    Negative Logits
    arist
    -0.88
    iques
    -0.85
    hes
    -0.78
    iasis
    -0.76
    warts
    -0.72
    irez
    -0.71
    ness
    -0.70
    immer
    -0.68
    este
    -0.68
    rarily
    -0.67
    POSITIVE LOGITS
    å¹
    0.78
     onwards
    0.75
     expiration
    0.72
    etheus
    0.68
     deadline
    0.68
     onward
    0.67
    lled
    0.65
     TBD
    0.64
    2019
    0.64
    HUD
    0.63
    Activations Density 0.016%

    No Known Activations