© 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. 15394
    Prev
    Next
    INDEX
    Explanations

    statements that are expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    55
    +0.18
    0.8%
    125
    +0.11
    0.5%
    7
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.18
    0.08
    125
    +0.11
    0.05
    690
    +0.10
    0.04
    Negative Logits
    luaj
    -0.69
    bies
    -0.68
     IMAGES
    -0.66
    igraph
    -0.64
    ertodd
    -0.64
     bunch
    -0.64
     Finish
    -0.63
    esm
    -0.60
     Bung
    -0.60
    uffs
    -0.60
    POSITIVE LOGITS
     unclear
    1.17
     imperative
    1.09
     doubtful
    1.09
     impossible
    1.06
     unlikely
    1.05
     advisable
    1.04
     conceivable
    0.99
     indeed
    0.98
     undeniable
    0.97
     easier
    0.95
    Activations Density 0.106%

    No Known Activations