© 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. 10817
    Prev
    Next
    INDEX
    Explanations

    negative sentiments and criticism within text

    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
    537
    +0.12
    0.6%
    102
    +0.12
    0.6%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.03
    102
    +0.12
    0.02
    152
    +0.10
    0.02
    Negative Logits
     Kamp
    -0.75
     Richards
    -0.75
     AVG
    -0.72
     Cecil
    -0.72
     Finch
    -0.69
     Klaus
    -0.69
     Reed
    -0.69
     Hoo
    -0.68
     Roe
    -0.68
     Zar
    -0.67
    POSITIVE LOGITS
    dimensional
    1.43
    functional
    1.28
    ethnic
    1.16
    disciplinary
    1.16
    purpose
    1.14
    digit
    1.13
    colored
    1.13
    format
    1.12
    touch
    1.11
    sided
    1.10
    Activations Density 0.014%

    No Known Activations