© 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. 16512
    Prev
    Next
    INDEX
    Explanations

    architectural and design-related terms and descriptions

    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
    481
    +0.10
    0.5%
    683
    +0.10
    0.4%
    474
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.10
    0.06
    683
    +0.10
    0.05
    267
    +0.10
    0.05
    Negative Logits
    itars
    -0.68
     Valve
    -0.63
     ammon
    -0.63
     awoken
    -0.62
    unts
    -0.62
    anical
    -0.62
     taxing
    -0.60
     drums
    -0.59
     federally
    -0.59
    orate
    -0.58
    POSITIVE LOGITS
     Magazine
    1.39
    Magazine
    1.34
     magazine
    1.27
     Editorial
    1.21
     editorial
    1.11
     editors
    1.09
     article
    1.08
    News
    1.07
     Weekly
    1.04
     columnist
    1.03
    Activations Density 0.201%

    No Known Activations