© 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. 10368
    Prev
    Next
    INDEX
    Explanations

    content related to political and societal issues, with a focus on criticism and opinions

    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
    87
    +0.23
    1.2%
    373
    +0.12
    0.6%
    358
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.23
    -0.03
    298
    +0.12
    0.05
    358
    +0.12
    0.04
    Negative Logits
    externalActionCode
    -0.73
    DragonMagazine
    -0.69
    osponsors
    -0.63
    asio
    -0.60
    taboola
    -0.57
     Medline
    -0.57
    imon
    -0.57
    illin
    -0.57
    lycer
    -0.56
    phabet
    -0.54
    POSITIVE LOGITS
     theirs
    0.82
     anymore
    0.69
     innoc
    0.68
     ignor
    0.67
     slightest
    0.65
     injust
    0.65
     transpired
    0.65
     inconven
    0.63
     THEIR
    0.63
     supposedly
    0.62
    Activations Density 0.939%

    No Known Activations