© 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 EvalsExportsAPI 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. 6100
    Prev
    Next
    INDEX
    Explanations

    keywords related to actions or events happening physically in a specific context

    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
    681
    +0.11
    0.5%
    481
    +0.10
    0.5%
    47
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.11
    0.06
    665
    +0.10
    0.05
    469
    +0.10
    0.03
    Negative Logits
    76561
    -0.69
    gui
    -0.66
    deal
    -0.63
     reckoning
    -0.63
    geoning
    -0.63
     estimating
    -0.63
    gnu
    -0.62
    fortunately
    -0.61
    eria
    -0.60
    croft
    -0.60
    POSITIVE LOGITS
     hay
    0.73
     furiously
    0.71
    pherd
    0.69
    ersive
    0.67
     HIS
    0.64
     merry
    0.59
    oji
    0.58
    ictionary
    0.58
    bird
    0.57
    HAM
    0.57
    Activations Density 0.288%

    No Known Activations