© 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 EvalsExportsinterp-engineNEWAPI 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. 22561
    Prev
    Next
    INDEX
    Explanations

    references to publications and media outlets

    oai_token-act-pair · gpt-4o-miniTriggered 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
    480
    +0.58
    3.5%
    87
    +0.30
    1.8%
    266
    +0.19
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.58
    0.03
    266
    +0.30
    0.09
    314
    +0.19
    -0.00
    Negative Logits
     awa
    -0.67
     disadvant
    -0.54
     punishing
    -0.53
    avorite
    -0.53
     enrich
    -0.51
     grandchildren
    -0.51
     unrecogn
    -0.51
     shove
    -0.51
     outwe
    -0.49
     stripping
    -0.48
    POSITIVE LOGITS
    photos
    0.61
    Poll
    0.61
    ipedia
    0.60
    pedia
    0.59
     Analytics
    0.58
    ickr
    0.56
     Architects
    0.56
     Interactive
    0.56
    Scot
    0.55
    blog
    0.55
    Activations Density 0.821%

    No Known Activations