© 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. 13500
    Prev
    Next
    INDEX
    Explanations

    quotations within 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
    481
    +0.11
    0.5%
    640
    +0.11
    0.5%
    255
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.11
    0.05
    240
    +0.11
    0.05
    255
    +0.09
    0.05
    Negative Logits
     arch
    -0.73
     lineage
    -0.70
     vault
    -0.69
     spine
    -0.69
     spr
    -0.69
     sprint
    -0.69
     upstairs
    -0.67
     pir
    -0.67
     repro
    -0.67
     prec
    -0.66
    POSITIVE LOGITS
    We
    1.44
    Our
    1.36
    There
    1.34
    Because
    1.31
    It
    1.31
    People
    1.30
    Certainly
    1.29
    Unless
    1.29
    Today
    1.28
    These
    1.27
    Activations Density 0.109%

    No Known Activations