© 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. 21241
    Prev
    Next
    INDEX
    Explanations

    bullet points and numerical lists

    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
    640
    +0.19
    0.9%
    385
    +0.09
    0.4%
    304
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.04
    176
    +0.09
    0.03
    6
    +0.09
    0.03
    Negative Logits
     haun
    -0.74
    guards
    -0.71
     tides
    -0.67
     overlooked
    -0.66
     neighb
    -0.66
     swinging
    -0.65
     spoiled
    -0.64
     dared
    -0.64
     overflowing
    -0.63
     spilled
    -0.63
    POSITIVE LOGITS
     Introduction
    1.22
     [+
    1.09
     Firstly
    0.95
     Definitions
    0.94
     Overview
    0.93
     Purpose
    0.91
     Differences
    0.87
     Conclusion
    0.85
    jpg
    0.85
     Thou
    0.85
    Activations Density 0.063%

    No Known Activations