© 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. 5018
    Prev
    Next
    INDEX
    Explanations

    algorithms and technical terms related to computer hardware and software

    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
    374
    +0.10
    0.4%
    713
    +0.09
    0.4%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.10
    0.04
    575
    +0.09
    0.04
    325
    +0.09
    0.03
    Negative Logits
    livion
    -0.72
    verages
    -0.63
    vich
    -0.60
     Droid
    -0.60
    politics
    -0.59
    osity
    -0.59
    racuse
    -0.58
    oÄŁ
    -0.57
    \\\\\\\\\\\\\\\\
    -0.57
     Veh
    -0.57
    POSITIVE LOGITS
    mith
    1.26
    hips
    1.24
    hops
    1.15
    uggest
    1.04
    hooting
    0.95
    pring
    0.95
    creen
    0.94
    heet
    0.93
    paces
    0.92
    chool
    0.92
    Activations Density 0.122%

    No Known Activations