© 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. 4244
    Prev
    Next
    INDEX
    Explanations

    announcements and acknowledgments in a professional or official context

    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
    125
    +0.11
    0.5%
    55
    +0.11
    0.5%
    463
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.11
    0.04
    685
    +0.11
    0.03
    13
    +0.09
    0.06
    Negative Logits
    uggle
    -0.73
     stuff
    -0.70
     monop
    -0.70
     IQ
    -0.69
     hybrids
    -0.68
     trickle
    -0.68
     mole
    -0.68
     infiltration
    -0.66
    stuff
    -0.64
     supposedly
    -0.63
    POSITIVE LOGITS
     THANK
    1.30
     thank
    1.29
     congratulations
    1.23
     saddened
    1.21
     commend
    1.20
     hereby
    1.19
     grateful
    1.18
     rejoice
    1.16
     congratulate
    1.16
     heartfelt
    1.16
    Activations Density 0.744%

    No Known Activations