© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14754
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or events in news stories

    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
    627
    +0.15
    0.7%
    373
    +0.14
    0.6%
    409
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.15
    0.03
    409
    +0.14
    0.02
    501
    +0.12
    0.02
    Negative Logits
     apes
    -0.70
     craw
    -0.70
     prol
    -0.68
     shame
    -0.67
     worms
    -0.67
     idol
    -0.65
     stare
    -0.65
     pests
    -0.64
     mosquitoes
    -0.64
     cynicism
    -0.64
    POSITIVE LOGITS
    Getty
    1.10
    Jac
    0.96
    File
    0.94
    Special
    0.90
    WAR
    0.90
    Bloomberg
    0.90
    Charles
    0.89
    Las
    0.89
    Mike
    0.88
    Creat
    0.88
    Activations Density 0.015%

    No Known Activations