© 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. 4020
    Prev
    Next
    INDEX
    Explanations

    the word "captagon" or variations of it, potentially related to news articles or information about the drug

    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
    526
    +0.12
    0.6%
    223
    +0.12
    0.6%
    238
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.12
    0.01
    223
    +0.12
    0.01
    232
    +0.11
    0.01
    Negative Logits
     trust
    -0.65
     Catalyst
    -0.64
     paternity
    -0.63
     Tend
    -0.63
     crowdfunding
    -0.62
     inclined
    -0.61
     onwards
    -0.61
     Shattered
    -0.60
     aside
    -0.60
     Centauri
    -0.60
    POSITIVE LOGITS
    aining
    1.33
    ained
    1.30
    ains
    1.29
    ivating
    1.28
    ions
    1.24
    iors
    1.14
    ivated
    1.07
    orable
    1.06
    urable
    1.06
    ured
    1.05
    Activations Density 0.017%

    No Known Activations