© 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. 1945
    Prev
    Next
    INDEX
    Explanations

    adjectives related to evaluations and opinions

    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
    411
    +0.13
    0.6%
    394
    +0.12
    0.6%
    38
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.13
    0.04
    522
    +0.12
    0.03
    559
    +0.12
    0.03
    Negative Logits
    âĵĺ
    -0.77
    urrence
    -0.65
    lier
    -0.65
     fundament
    -0.64
    Materials
    -0.64
    backer
    -0.64
    ieves
    -0.62
    foreseen
    -0.61
     installments
    -0.60
    etts
    -0.60
    POSITIVE LOGITS
     technically
    0.89
     initially
    0.76
     tempting
    0.72
     disagree
    0.72
     superf
    0.71
     flashy
    0.68
     intimidating
    0.67
     surprising
    0.66
    inventoryQuantity
    0.64
     cliché
    0.64
    Activations Density 0.127%

    No Known Activations