© 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. 3636
    Prev
    Next
    INDEX
    Explanations

    questions related to decision-making and actions of individuals or organizations

    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
    191
    +0.10
    0.5%
    86
    +0.10
    0.5%
    285
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.08
    546
    +0.10
    0.08
    720
    +0.10
    0.09
    Negative Logits
    atars
    -0.70
    ãĤ£
    -0.68
    iple
    -0.66
     Kodi
    -0.64
     CLR
    -0.63
    KC
    -0.61
     directional
    -0.60
     corrid
    -0.59
     KH
    -0.58
     Thermal
    -0.56
    POSITIVE LOGITS
     lest
    1.13
     namely
    1.05
     albeit
    0.97
     irrespective
    0.91
     despite
    0.90
     especially
    0.90
     culminating
    0.88
     viz
    0.88
     particularly
    0.88
     regardless
    0.86
    Activations Density 0.422%

    No Known Activations