© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19433
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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
    508
    +0.15
    0.7%
    288
    +0.11
    0.5%
    538
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.15
    0.03
    295
    +0.11
    0.02
    656
    +0.09
    0.02
    Negative Logits
    chnology
    -0.77
     innocence
    -0.67
     Lauder
    -0.63
    holding
    -0.63
    pora
    -0.63
    ãĤ©
    -0.62
     wart
    -0.61
    ngth
    -0.61
     Macintosh
    -0.60
     indign
    -0.60
    POSITIVE LOGITS
    iterranean
    1.32
    ieval
    1.23
    ication
    1.18
    itations
    1.18
    ications
    1.18
    itated
    1.11
    ulla
    1.11
    itating
    1.10
    icated
    1.10
    allion
    1.10
    Activations Density 0.031%

    No Known Activations