© 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. 4513
    Prev
    Next
    INDEX
    Explanations

    data-related terms such as numbers, statistics, and analysis

    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
    481
    +0.16
    0.7%
    177
    +0.10
    0.4%
    490
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.16
    0.05
    362
    +0.10
    0.04
    172
    +0.10
    0.03
    Negative Logits
    oided
    -0.77
    itiz
    -0.70
     warr
    -0.66
     dunno
    -0.65
     recovers
    -0.65
    erate
    -0.64
    icide
    -0.64
    orius
    -0.64
    scribe
    -0.63
    mouth
    -0.63
    POSITIVE LOGITS
     screenshots
    0.85
     pictures
    0.75
     glances
    0.74
     appearances
    0.74
     recent
    0.72
     glimps
    0.72
     Rasmussen
    0.71
     fact
    0.70
     Figures
    0.69
     comments
    0.69
    Activations Density 0.233%

    No Known Activations