© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11925
    Prev
    Next
    INDEX
    Explanations

    patent-related terms and statuses

    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
    373
    +0.17
    0.8%
    383
    +0.10
    0.5%
    316
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.17
    0.04
    316
    +0.10
    0.03
    373
    +0.10
    -0.02
    Negative Logits
    vernment
    -0.67
     coerc
    -0.65
    zynski
    -0.65
    Reviewer
    -0.64
    ilitary
    -0.62
     redistributed
    -0.61
     transfers
    -0.59
     reconc
    -0.59
    bler
    -0.57
     cannabin
    -0.56
    POSITIVE LOGITS
     Featuring
    0.72
     TBD
    0.71
    reviewed
    0.69
     Required
    0.68
     Remix
    0.67
     1862
    0.66
    Requires
    0.66
     01
    0.65
     1024
    0.64
     Available
    0.64
    Activations Density 0.157%

    No Known Activations