© 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. 13532
    Prev
    Next
    INDEX
    Explanations

    URLs containing numbers

    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
    326
    +0.14
    0.6%
    375
    +0.12
    0.5%
    587
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.03
    316
    +0.12
    0.03
    719
    +0.10
    0.04
    Negative Logits
    istically
    -0.76
    board
    -0.74
    mers
    -0.73
    estine
    -0.72
    lined
    -0.72
    mast
    -0.70
    etary
    -0.69
    coat
    -0.69
    icial
    -0.68
    hetically
    -0.67
    POSITIVE LOGITS
     ILCS
    0.83
    çĶŁ
    0.76
    ãĥ´ãĤ¡
    0.72
    288
    0.72
    âĸĪ
    0.69
     MHz
    0.68
    381
    0.66
    806
    0.66
    BLIC
    0.65
    REM
    0.65
    Activations Density 0.068%

    No Known Activations