© 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. 3311
    Prev
    Next
    INDEX
    Explanations

    names of different locations

    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
    373
    +0.21
    1.1%
    459
    +0.14
    0.7%
    481
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.21
    -0.05
    339
    +0.14
    0.04
    561
    +0.13
    0.05
    Negative Logits
    —"
    -0.73
    thumbnails
    -0.73
    RESULTS
    -0.71
     UNCLASSIFIED
    -0.69
     afterward
    -0.68
    âĹ¼
    -0.65
    CONCLUS
    -0.65
    )."
    -0.65
    ··
    -0.63
    etheless
    -0.62
    POSITIVE LOGITS
    reetings
    0.85
    ONDON
    0.69
     SHARES
    0.67
     Updated
    0.67
     Published
    0.62
     awoke
    0.62
    ldon
    0.59
     Yesterday
    0.58
     Introduction
    0.56
     Latest
    0.56
    Activations Density 0.793%

    No Known Activations