© 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. 3071
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific words or phrases

    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
    269
    +0.11
    0.5%
    581
    +0.10
    0.5%
    654
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.11
    0.04
    654
    +0.10
    0.04
    90
    +0.10
    0.04
    Negative Logits
    asma
    -0.63
    orically
    -0.62
    Jose
    -0.56
     reprinted
    -0.56
    ress
    -0.56
    Attempts
    -0.56
    irl
    -0.56
    Residents
    -0.55
    asher
    -0.55
    acies
    -0.55
    POSITIVE LOGITS
    stage
    1.11
     board
    1.09
     rooft
    1.01
    etime
    0.93
    shore
    0.91
     stage
    0.90
     behalf
    0.88
    site
    0.88
    boarding
    0.88
    screen
    0.87
    Activations Density 0.101%

    No Known Activations