© 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. 9052
    Prev
    Next
    INDEX
    Explanations

    cases where someone needs to apologize or show solidarity

    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
    314
    +0.16
    0.7%
    640
    +0.13
    0.6%
    480
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.07
    6
    +0.13
    0.06
    314
    +0.13
    0.00
    Negative Logits
     manif
    -0.83
    forth
    -0.73
     Syri
    -0.71
     chanting
    -0.68
     rebuilding
    -0.67
     suspending
    -0.67
    fman
    -0.66
     McF
    -0.66
     Gork
    -0.65
     scrambling
    -0.65
    POSITIVE LOGITS
    ategories
    1.33
     Browse
    1.07
    Category
    1.04
     Category
    1.01
    Rate
    0.99
    Login
    0.99
    Favorite
    0.98
    Description
    0.97
    Brow
    0.97
    Title
    0.96
    Activations Density 0.280%

    No Known Activations