© 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. 22951
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant amounts or degrees

    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
    447
    +0.15
    0.7%
    481
    +0.13
    0.6%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    632
    +0.15
    0.03
    43
    +0.13
    0.03
    356
    +0.10
    0.02
    Negative Logits
    minster
    -0.76
    SourceFile
    -0.74
    audi
    -0.66
    pecially
    -0.64
    formerly
    -0.64
    uran
    -0.62
    ADA
    -0.62
    çĶ°
    -0.61
    ãĥ³ãĤ¸
    -0.60
    onym
    -0.60
    POSITIVE LOGITS
     anecd
    0.89
     suffice
    0.88
     there
    0.85
     beware
    0.80
     nevertheless
    0.80
     nonetheless
    0.79
     please
    0.74
     somew
    0.74
     congr
    0.74
     Canaver
    0.72
    Activations Density 0.132%

    No Known Activations