© 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. 0-RES-JB
    11. 13292
    Prev
    Next
    INDEX
    Explanations

    verbs ending in '-ying'

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles, specifically words ending in "ying"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sustained
    -0.68
     wide
    -0.64
     ATP
    -0.63
     Scand
    -0.63
     tract
    -0.61
     charged
    -0.60
     modified
    -0.60
     mult
    -0.60
     summary
    -0.60
     compounded
    -0.59
    POSITIVE LOGITS
    ying
    4.48
    ied
    2.41
    YING
    1.94
    ies
    1.77
    ys
    1.50
    IED
    1.48
    iling
    1.24
    iness
    1.24
    ening
    1.14
    aying
    1.12
    Activations Density 0.011%

    No Known Activations