© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 7069
    Prev
    Next
    INDEX
    Explanations

    words related to writing, breathing, and sleep cycles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "write" in various forms related to the act of writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISON
    -0.66
    isu
    -0.65
    isma
    -0.63
    iano
    -0.62
     Garrison
    -0.62
    ĪĴ
    -0.60
    IST
    -0.59
    âĢ¢âĢ¢
    -0.59
    ison
    -0.59
    iren
    -0.58
    POSITIVE LOGITS
    hes
    1.28
    hing
    1.07
    hers
    1.05
    chers
    1.04
    ches
    1.01
    cher
    1.00
    htaking
    1.00
    hed
    0.95
    ched
    0.95
    he
    0.94
    Activations Density 0.288%

    No Known Activations