© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8706
    Prev
    Next
    INDEX
    Explanations

    references to royalty payments or agreements

    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
    288
    +0.14
    0.7%
    447
    +0.13
    0.6%
    418
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.04
    326
    +0.13
    0.03
    464
    +0.12
    0.02
    Negative Logits
    lihood
    -0.92
    fare
    -0.87
    crew
    -0.86
    aways
    -0.85
    colo
    -0.84
    nam
    -0.79
    gins
    -0.78
    stood
    -0.78
    loo
    -0.76
    yon
    -0.76
    POSITIVE LOGITS
    pell
    0.72
     decree
    0.71
    staking
    0.69
    ised
    0.66
     mort
    0.66
    idge
    0.66
    psey
    0.66
     athlet
    0.64
    idges
    0.63
    aic
    0.62
    Activations Density 0.089%

    No Known Activations