© 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. 10-RES-JB
    11. 16991
    Prev
    Next
    INDEX
    Explanations

    dates and structured data represented by special characters like 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    elements related to numerical data or statistics

    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
    ¥ŀ
    -0.80
     ende
    -0.78
     perv
    -0.75
     numbering
    -0.73
     citiz
    -0.72
     veter
    -0.71
     supers
    -0.71
     worry
    -0.68
     morphed
    -0.68
     tram
    -0.68
    POSITIVE LOGITS
    https
    1.42
    http
    1.42
    âĹı
    1.13
    âĢ¢
    1.12
    Spoiler
    1.08
    BuyableInstoreAndOnline
    1.05
    ·
    1.05
    Quote
    1.02
    Python
    0.97
    Interstitial
    0.97
    Activations Density 0.083%

    No Known Activations