© 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. 22579
    Prev
    Next
    INDEX
    Explanations

    advertising-related content and high-profile mentions or discussions of social and economic topics

    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
    314
    +0.11
    0.5%
    94
    +0.09
    0.4%
    481
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.06
    176
    +0.09
    0.04
    631
    +0.09
    0.05
    Negative Logits
    è¦ļéĨĴ
    -0.75
    MODE
    -0.73
     Fn
    -0.71
     Tacoma
    -0.67
     Ribbon
    -0.67
     initials
    -0.61
    ĵĺ
    -0.61
     LINE
    -0.60
     cig
    -0.59
    AU
    -0.59
    POSITIVE LOGITS
    vertising
    1.25
    roximately
    1.25
    withstanding
    1.17
    jamin
    1.17
    resa
    1.13
    xiety
    1.08
    icularly
    1.04
    elligence
    1.04
    cluding
    1.01
    ropolitan
    1.01
    Activations Density 0.176%

    No Known Activations