© 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. 22810
    Prev
    Next
    INDEX
    Explanations

    numerical data related to percentages in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    316
    +0.10
    0.5%
    26
    +0.09
    0.4%
    17
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.10
    0.04
    469
    +0.09
    0.03
    17
    +0.09
    0.03
    Negative Logits
    SpaceEngineers
    -0.56
    ffen
    -0.54
    Frameworks
    -0.54
     precon
    -0.54
     resize
    -0.51
    dayName
    -0.48
     Fres
    -0.48
    DragonMagazine
    -0.47
    WARE
    -0.47
    bda
    -0.46
    POSITIVE LOGITS
     33
    1.32
     32
    1.31
     36
    1.29
     37
    1.28
     34
    1.27
     53
    1.27
     46
    1.27
     8
    1.26
     39
    1.26
     47
    1.25
    Activations Density 0.195%

    No Known Activations