© 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 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. 7674
    Prev
    Next
    INDEX
    Explanations

    words related to discussions or debates on policies, agreements, and decisions

    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
    449
    +0.10
    0.5%
    588
    +0.10
    0.5%
    762
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.10
    0.05
    331
    +0.10
    0.04
    227
    +0.10
    0.02
    Negative Logits
    bryce
    -0.63
    opa
    -0.62
     Babel
    -0.58
    nexus
    -0.56
    gio
    -0.55
    uru
    -0.55
    (){
    -0.55
    ļéĨĴ
    -0.54
    DragonMagazine
    -0.53
    aepernick
    -0.52
    POSITIVE LOGITS
     ones
    0.67
    cially
    0.63
    yond
    0.62
     detriment
    0.62
    vable
    0.61
    phy
    0.61
    etheless
    0.60
    astrous
    0.59
    cffffcc
    0.59
    arse
    0.59
    Activations Density 0.395%

    No Known Activations