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. 10-RES-JB
    6. 375
    Prev
    Next
    INDEX
    Explanations

    verbs and adverbs related to slow and gradual processes

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating a gradual progression or change

    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
    ilion
    -0.82
    blance
    -0.82
    ãĥ¤
    -0.79
    aucus
    -0.73
    lua
    -0.71
     Parables
    -0.70
    DERR
    -0.68
    POSE
    -0.67
    quickShipAvailable
    -0.67
    halla
    -0.66
    POSITIVE LOGITS
     trickle
    1.04
     creeping
    1.02
     phased
    1.01
     decreasing
    0.99
     progressing
    0.97
     dwindling
    0.95
     increasing
    0.95
     crept
    0.94
     dwind
    0.93
     drifting
    0.93
    Activations Density 0.043%

    No Known Activations