© 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. 16065
    Prev
    Next
    INDEX
    Explanations

    negative or critical language regarding a subject or situation

    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
    738
    +0.12
    0.5%
    35
    +0.12
    0.5%
    271
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.01
    738
    +0.12
    0.01
    374
    +0.12
    0.01
    Negative Logits
    DragonMagazine
    -0.72
    nda
    -0.68
    ouf
    -0.67
    20439
    -0.66
    tis
    -0.65
     rall
    -0.62
    isable
    -0.62
     Pavilion
    -0.62
     Grac
    -0.62
    ATIONAL
    -0.62
    POSITIVE LOGITS
    asses
    1.01
     dick
    1.01
    driver
    0.95
    eries
    0.93
    loads
    0.92
    shit
    0.90
     suck
    0.84
    sylvania
    0.83
    drivers
    0.80
    ride
    0.79
    Activations Density 0.025%

    No Known Activations