Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11677
    Prev
    Next
    INDEX
    Explanations

    keywords related to cleanliness and hygiene

    oai_token-act-pair · gpt-3.5-turbo

    words associated with environmental cleanliness and sustainability

    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
     Kut
    -0.71
     dominion
    -0.70
    RPG
    -0.69
    DragonMagazine
    -0.67
     Thrones
    -0.66
    ãĥĥãĥī
    -0.63
    Ka
    -0.63
    held
    -0.62
     dreaded
    -0.62
     Peaks
    -0.61
    POSITIVE LOGITS
    mson
    0.97
     cleaner
    0.97
     fres
    0.94
     Fres
    0.92
    gas
    0.82
    ogly
    0.78
    instein
    0.76
     cleaners
    0.76
     ammon
    0.76
    ineries
    0.74
    Activations Density 0.014%

    No Known Activations