© 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. 18764
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    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
    69
    +0.12
    0.5%
    82
    +0.11
    0.5%
    340
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.04
    105
    +0.11
    0.04
    82
    +0.10
    0.05
    Negative Logits
    thood
    -0.78
     nour
    -0.70
    worth
    -0.69
    ynes
    -0.68
    SPONSORED
    -0.66
     empowering
    -0.66
    Merit
    -0.66
    oire
    -0.66
    nai
    -0.65
    ensable
    -0.64
    POSITIVE LOGITS
     typo
    1.62
     errors
    1.54
     inaccur
    1.52
     error
    1.39
     inconsistencies
    1.37
     inconsistency
    1.35
     glitches
    1.34
     misinterpret
    1.30
     discrepancies
    1.29
     inacc
    1.28
    Activations Density 0.970%

    No Known Activations