© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 8463
    Prev
    Next
    INDEX
    Explanations

    verbs related to quitting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quit" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inen
    -0.79
    Catalog
    -0.76
    arov
    -0.69
    ANS
    -0.69
    Herm
    -0.67
    Grant
    -0.62
     ancest
    -0.62
    arthy
    -0.62
    ---------------
    -0.62
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.60
    POSITIVE LOGITS
     smoking
    1.13
    ters
    0.99
     Smoking
    0.92
    ting
    0.92
     Quit
    0.87
     quitting
    0.82
     whining
    0.76
    smoking
    0.75
     eating
    0.69
    terness
    0.67
    Activations Density 0.009%

    No Known Activations