© 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. 20969
    Prev
    Next
    INDEX
    Explanations

    keywords related to media, specifically TV shows and movies, along with some technical details like memory issues

    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
    +0.21
    1.1%
    447
    +0.16
    0.8%
    739
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.07
    659
    +0.16
    0.06
    464
    +0.09
    0.05
    Negative Logits
    STDOUT
    -0.59
    blance
    -0.56
     destro
    -0.55
     notor
    -0.55
    undai
    -0.54
     psychiat
    -0.54
     tremend
    -0.54
    olulu
    -0.53
     broader
    -0.53
     pestic
    -0.53
    POSITIVE LOGITS
     ->
    0.87
     |
    0.83
     ·
    0.83
     [/
    0.80
     âľ
    0.77
     [-
    0.74
     -->
    0.74
     */
    0.72
     |--
    0.71
    ↵
    0.71
    Activations Density 0.788%

    No Known Activations