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

    Neuronpedia

    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. 1-RES-JB
    11. 14330
    Prev
    Next
    INDEX
    Explanations

    numbers followed by the word "page"

    oai_token-act-pair · gpt-3.5-turbo

    references to page numbers in a document

    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
    ALLY
    -0.72
     Universal
    -0.67
     mids
    -0.66
     propensity
    -0.66
    dayName
    -0.65
     Strikes
    -0.58
     Rockies
    -0.58
     denomin
    -0.57
     Caps
    -0.57
    Interstitial
    -0.56
    POSITIVE LOGITS
    page
    1.34
    pages
    1.10
    views
    1.09
    antry
    1.03
     pages
    1.01
    Page
    0.97
     page
    0.90
    Pages
    0.86
    oldown
    0.85
    folios
    0.81
    Activations Density 0.010%

    No Known Activations