© 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. 5698
    Prev
    Next
    INDEX
    Explanations

    personal accounts and stories

    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
    762
    +0.12
    0.6%
    393
    +0.12
    0.6%
    370
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.12
    0.10
    139
    +0.12
    0.09
    762
    +0.12
    0.10
    Negative Logits
    pires
    -0.75
     Initiative
    -0.74
     Globe
    -0.70
     Consortium
    -0.67
     Question
    -0.63
     Rough
    -0.62
     Billion
    -0.60
     Outside
    -0.59
     Observatory
    -0.58
     Silicon
    -0.58
    POSITIVE LOGITS
     knew
    1.50
     hadn
    1.42
     didnt
    1.39
     didn
    1.37
    'd
    1.37
     did
    1.24
    didn
    1.24
     saw
    1.23
     couldn
    1.22
     had
    1.21
    Activations Density 0.440%

    No Known Activations