© 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. 16710
    Prev
    Next
    INDEX
    Explanations

    definitions or explanations of terms or concepts

    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
    549
    +0.11
    0.5%
    238
    +0.11
    0.5%
    32
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.11
    0.03
    261
    +0.11
    0.03
    332
    +0.11
    0.03
    Negative Logits
    umbn
    -0.85
    edom
    -0.76
    airs
    -0.76
    otos
    -0.70
    ordan
    -0.67
    apes
    -0.60
    SpaceEngineers
    -0.59
    é¾į
    -0.58
    DragonMagazine
    -0.57
     roundup
    -0.56
    POSITIVE LOGITS
     therein
    0.83
     firmly
    0.79
    igating
    0.78
     within
    0.75
     beneath
    0.72
     squarely
    0.70
    ged
    0.69
     rooted
    0.69
    ined
    0.68
     solely
    0.68
    Activations Density 0.083%

    No Known Activations