© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 13414
    Prev
    Next
    INDEX
    Explanations

    instances where someone quits something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quit" and its variations, indicating discussions around cessation or stopping actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maid
    -0.61
    acqu
    -0.60
     Sorceress
    -0.60
    ammy
    -0.59
     intric
    -0.59
    achusetts
    -0.58
    ENCY
    -0.58
    Herm
    -0.57
     Quarterly
    -0.57
     Roose
    -0.56
    POSITIVE LOGITS
     quit
    1.18
     quitting
    1.13
     Quit
    1.13
    ters
    0.97
    ccoli
    0.86
     smoking
    0.85
    reat
    0.77
    escape
    0.73
     reinvent
    0.71
    quit
    0.70
    Activations Density 0.006%

    No Known Activations