© 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. 20926
    Prev
    Next
    INDEX
    Explanations

    dates in the format 'Month, Year'

    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
    87
    +0.25
    1.3%
    373
    +0.11
    0.6%
    464
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.25
    0.05
    711
    +0.11
    0.03
    87
    +0.10
    -0.03
    Negative Logits
    iland
    -0.66
    uddin
    -0.56
    enhagen
    -0.52
    gae
    -0.47
     distracted
    -0.46
     Samoa
    -0.45
    INGTON
    -0.45
    risome
    -0.45
     Anat
    -0.44
     Father
    -0.44
    POSITIVE LOGITS
    Dialogue
    0.63
    ciation
    0.59
    ierre
    0.59
    ħĭ
    0.58
    endment
    0.55
    lege
    0.54
    ij士
    0.53
    iste
    0.53
    earances
    0.53
    alion
    0.53
    Activations Density 0.761%

    No Known Activations