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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 21631
    Prev
    Next
    INDEX
    Explanations

    words ending in '-edly'

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and adverbs describing actions or qualities

    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
     FANT
    -0.58
    ocations
    -0.58
    anders
    -0.57
    ioxide
    -0.56
    aterial
    -0.55
    angs
    -0.55
     fateful
    -0.54
     Dickinson
    -0.52
    conservancy
    -0.52
    AAF
    -0.50
    POSITIVE LOGITS
    ly
    3.65
    LY
    2.59
    lys
    1.67
    edly
    1.65
    fully
    1.64
    lly
    1.63
    ially
    1.55
    ELY
    1.54
    liness
    1.52
    ously
    1.52
    Activations Density 0.583%

    No Known Activations