© 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. 16673
    Prev
    Next
    INDEX
    Explanations

    details related to news updates delivered by email

    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
    306
    +0.10
    0.5%
    361
    +0.09
    0.4%
    350
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.10
    0.01
    531
    +0.09
    0.01
    361
    +0.09
    0.01
    Negative Logits
    conn
    -0.78
    wikipedia
    -0.75
    perty
    -0.63
    appropri
    -0.60
    é¾įå
    -0.59
    odan
    -0.58
     conce
    -0.57
    mare
    -0.57
     denomin
    -0.56
    bach
    -0.56
    POSITIVE LOGITS
     delivered
    0.90
    imentary
    0.83
     weekday
    0.81
    Interstitial
    0.79
     Subscribe
    0.75
     subscribe
    0.72
     personalized
    0.70
     electronically
    0.69
    ivered
    0.69
    ocument
    0.66
    Activations Density 0.013%

    No Known Activations