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

    Neuronpedia

    Jacobian LensNEW
    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. 6044
    Prev
    Next
    INDEX
    Explanations

    biomedical terms and procedures related to medical research and treatment

    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
    691
    +0.13
    0.6%
    105
    +0.11
    0.5%
    150
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    691
    +0.13
    0.04
    469
    +0.11
    0.03
    239
    +0.10
    0.03
    Negative Logits
    think
    -0.79
    doesn
    -0.75
     someday
    -0.74
    something
    -0.72
    hello
    -0.71
    etsy
    -0.71
    Think
    -0.68
    uably
    -0.68
     yours
    -0.67
    whatever
    -0.67
    POSITIVE LOGITS
     hist
    1.01
    alyses
    1.00
     assay
    1.00
     âĪ¼
    0.98
     randomized
    0.98
     analysed
    0.98
     analyses
    0.97
     validated
    0.95
     Participants
    0.95
     analyzed
    0.93
    Activations Density 0.416%

    No Known Activations