© 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. 17190
    Prev
    Next
    INDEX
    Explanations

    names of people or locations

    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
    378
    +0.13
    0.6%
    114
    +0.10
    0.5%
    39
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    586
    +0.13
    0.03
    559
    +0.10
    0.02
    220
    +0.10
    0.03
    Negative Logits
    rats
    -0.63
    patient
    -0.63
     follows
    -0.58
     conver
    -0.58
    luaj
    -0.58
    \":
    -0.57
     concluded
    -0.55
    âĵĺ
    -0.55
     concludes
    -0.55
    %:
    -0.54
    POSITIVE LOGITS
    ulton
    0.89
     IMAGES
    0.87
    Courtesy
    0.85
    querque
    0.85
     Photography
    0.84
     Courtesy
    0.83
     Caption
    0.82
    )</
    0.79
    thumbnails
    0.78
    verett
    0.77
    Activations Density 0.066%

    No Known Activations