© 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. 6857
    Prev
    Next
    INDEX
    Explanations

    references to age ranges

    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
    314
    +0.10
    0.4%
    382
    +0.10
    0.4%
    605
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.10
    0.03
    269
    +0.10
    0.03
    583
    +0.09
    0.02
    Negative Logits
     havoc
    -0.71
     Wast
    -0.70
    atl
    -0.66
    Quotes
    -0.66
     Subtle
    -0.63
    ity
    -0.62
    Voice
    -0.61
     goodbye
    -0.60
     Airl
    -0.60
     ACTIONS
    -0.59
    POSITIVE LOGITS
    ileged
    0.98
     age
    0.98
     ages
    0.81
    represented
    0.77
     whom
    0.77
     lvl
    0.75
     18
    0.75
    married
    0.73
    insured
    0.73
     eighteen
    0.72
    Activations Density 0.135%

    No Known Activations