© 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. 8617
    Prev
    Next
    INDEX
    Explanations

    the name "Evan" in various contexts

    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
    721
    +0.13
    0.6%
    578
    +0.12
    0.6%
    571
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    606
    +0.13
    0.01
    659
    +0.12
    0.01
    443
    +0.12
    0.01
    Negative Logits
    inals
    -0.65
     CFR
    -0.62
     insensitive
    -0.62
    giving
    -0.62
    orie
    -0.60
     Examiner
    -0.59
    ndum
    -0.58
     losers
    -0.58
     CoC
    -0.57
     lodge
    -0.57
    POSITIVE LOGITS
     Spiegel
    1.03
    ston
    1.00
    igans
    0.81
    odox
    0.81
     Gree
    0.81
    ildo
    0.81
    thal
    0.80
    esc
    0.78
    ufact
    0.77
    ium
    0.77
    Activations Density 0.031%

    No Known Activations