© 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. 8803
    Prev
    Next
    INDEX
    Explanations

    tech support related information

    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
    464
    +0.11
    0.5%
    174
    +0.11
    0.5%
    213
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.11
    0.02
    464
    +0.11
    0.02
    9
    +0.10
    0.02
    Negative Logits
     ASC
    -0.68
     Icelandic
    -0.68
     Kubrick
    -0.68
     Iceland
    -0.67
     Elves
    -0.66
     Encyclopedia
    -0.62
     bed
    -0.61
     trout
    -0.60
     knot
    -0.59
    lihood
    -0.59
    POSITIVE LOGITS
    phasis
    1.43
    otional
    1.43
    otions
    1.39
    otion
    1.33
    brace
    1.28
    igrant
    1.25
    perors
    1.22
    phas
    1.22
    igrants
    1.21
    igration
    1.20
    Activations Density 0.019%

    No Known Activations