© 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. 4648
    Prev
    Next
    INDEX
    Explanations

    descriptions of effective methods or tools for specific tasks

    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
    145
    +0.10
    0.4%
    240
    +0.09
    0.4%
    705
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.10
    0.04
    705
    +0.09
    0.03
    341
    +0.09
    0.03
    Negative Logits
    usters
    -0.88
    ĸļ
    -0.83
    uster
    -0.80
    aples
    -0.73
    inders
    -0.68
    noxious
    -0.67
    è¦ļéĨĴ
    -0.67
    ynski
    -0.66
    inately
    -0.64
    oppable
    -0.63
    POSITIVE LOGITS
    fare
    1.25
    finding
    1.19
    point
    1.03
    ward
    1.00
    forward
    0.99
     forward
    0.91
    finder
    0.88
    points
    0.87
    kell
    0.81
    station
    0.78
    Activations Density 0.041%

    No Known Activations