© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1658
    Prev
    Next
    INDEX
    Explanations

    references to time spent doing physical activities or tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to personal time management and scheduling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.71
     likeness
    -0.70
    entity
    -0.69
     authoritative
    -0.65
    object
    -0.64
    worthiness
    -0.64
    èĢħ
    -0.64
    oliath
    -0.62
    Versions
    -0.62
    ifiable
    -0.61
    POSITIVE LOGITS
     evenings
    1.30
     brunch
    1.29
     breakfast
    1.26
    aturday
    1.25
     mornings
    1.23
     weekends
    1.23
     lunch
    1.21
     afternoon
    1.21
    morning
    1.17
     dinner
    1.17
    Activations Density 0.736%

    No Known Activations