© 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. 10-RES-JB
    11. 20610
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with an emphasis on a small amount or a certain level of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a small amount or degree of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivable
    -0.75
    idth
    -0.69
    ategories
    -0.67
    orthy
    -0.67
    abad
    -0.66
    emale
    -0.64
    osponsors
    -0.64
    ovies
    -0.62
    ursed
    -0.61
    urdy
    -0.61
    POSITIVE LOGITS
    terness
    0.92
    mask
    0.82
     of
    0.82
    ching
    0.81
    ches
    0.75
    umen
    0.75
    maps
    0.74
    chery
    0.71
    meal
    0.71
     overboard
    0.71
    Activations Density 0.038%

    No Known Activations