© 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. 1-RES-JB
    11. 3723
    Prev
    Next
    INDEX
    Explanations

    mentions of the adverbs ending in '-ly'

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the suffix "ly" and related words expressing manner or quality

    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
    opol
    -1.01
    ese
    -0.84
    ibel
    -0.84
    lahoma
    -0.83
    rail
    -0.83
    atom
    -0.80
    hung
    -0.78
    adem
    -0.78
    ign
    -0.78
    acity
    -0.78
    POSITIVE LOGITS
    MY
    1.36
    WAYS
    1.35
    LY
    1.28
    BOOK
    1.22
    LINE
    1.19
    RY
    1.17
    COL
    1.12
    THING
    1.09
    FIL
    1.08
    WHERE
    1.07
    Activations Density 0.031%

    No Known Activations