© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18645
    Prev
    Next
    INDEX
    Explanations

    locations mentioned in text

    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
    659
    +0.17
    0.8%
    167
    +0.13
    0.6%
    348
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.17
    0.06
    348
    +0.13
    0.05
    126
    +0.12
    0.04
    Negative Logits
    ãĤ¡
    -0.74
     Bulg
    -0.73
     Isles
    -0.70
     friction
    -0.69
     Hera
    -0.66
    terday
    -0.64
     fortune
    -0.62
     Lerner
    -0.62
     Pose
    -0.61
     slurs
    -0.61
    POSITIVE LOGITS
    etermin
    1.29
    etermination
    1.28
    ownt
    1.28
    aughters
    1.19
    etermined
    1.17
    wayne
    1.16
    imensional
    1.15
    REAM
    1.14
    izzy
    1.14
    azz
    1.13
    Activations Density 0.037%

    No Known Activations