© 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. 22690
    Prev
    Next
    INDEX
    Explanations

    references to small businesses

    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
    669
    +0.15
    0.7%
    153
    +0.11
    0.5%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.15
    0.06
    153
    +0.11
    0.04
    65
    +0.10
    0.04
    Negative Logits
    reon
    -0.72
     largeDownload
    -0.69
     Rousse
    -0.66
    ILLE
    -0.65
     Michaels
    -0.65
    roit
    -0.64
    ophen
    -0.63
    ilee
    -0.61
    emy
    -0.60
    èĥ
    -0.60
    POSITIVE LOGITS
    pox
    1.35
     intestine
    1.06
     increments
    0.91
     sized
    0.91
     fry
    0.86
    folk
    0.86
     scale
    0.84
     stature
    0.84
    ota
    0.83
    scale
    0.82
    Activations Density 0.047%

    No Known Activations