© 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. 20769
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations and events

    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
    313
    +0.11
    0.5%
    409
    +0.10
    0.5%
    167
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.11
    0.02
    661
    +0.10
    0.02
    409
    +0.09
    0.02
    Negative Logits
    nery
    -0.69
     anytime
    -0.64
     commute
    -0.58
    ipation
    -0.56
     Dragonbound
    -0.55
     intrusion
    -0.55
     peg
    -0.55
     vomit
    -0.55
     tilt
    -0.54
     vibe
    -0.54
    POSITIVE LOGITS
    st
    1.23
    ī
    0.96
    Ĭ±
    0.95
    Īè
    0.89
    IJ
    0.89
    ĪĴ
    0.87
    stad
    0.85
    ļé
    0.84
    ĨĴ
    0.84
    sten
    0.83
    Activations Density 0.015%

    No Known Activations