© 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. 12123
    Prev
    Next
    INDEX
    Explanations

    information related to research studies and surveys

    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
    60
    +0.09
    0.4%
    686
    +0.09
    0.4%
    432
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.09
    0.04
    351
    +0.09
    0.03
    283
    +0.09
    0.01
    Negative Logits
    çīĪ
    -0.79
    iHUD
    -0.71
    DragonMagazine
    -0.69
    utsche
    -0.63
    displayText
    -0.62
    APTER
    -0.61
     confir
    -0.59
    iple
    -0.57
     Laser
    -0.54
     Panzer
    -0.54
    POSITIVE LOGITS
     themselves
    0.92
     rapists
    0.85
    their
    0.84
     psychologically
    0.80
     disproportionately
    0.77
     biologically
    0.77
     theirs
    0.75
     atheists
    0.75
     sexist
    0.75
     sexually
    0.73
    Activations Density 0.866%

    No Known Activations