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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 24192
    Prev
    Next
    INDEX
    Explanations

    references to the human digestive system, particularly the intestinal tract

    oai_token-act-pair · gpt-3.5-turbo

    references to the intestinal tract and related medical terminology

    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
    oken
    -0.74
    andra
    -0.71
     Photos
    -0.68
     decor
    -0.65
    erk
    -0.62
     Crimson
    -0.62
     Midnight
    -0.62
     Kob
    -0.62
     Skies
    -0.61
    iders
    -0.61
    POSITIVE LOGITS
     tract
    4.24
     tracts
    3.30
     parcel
    1.13
     tractor
    1.12
     parcels
    1.07
    ract
    1.01
     pamphlet
    0.96
     acre
    0.88
    bilt
    0.81
     pamph
    0.81
    Activations Density 0.011%

    No Known Activations