© 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. 11-RES-JB
    11. 7868
    Prev
    Next
    INDEX
    Explanations

    words related to the act of signing something into law

    oai_token-act-pair · gpt-3.5-turbo

    references to legislation being signed into law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asks
    -0.78
    mares
    -0.70
    nic
    -0.70
    burgh
    -0.63
    bey
    -0.63
    Ĥª
    -0.63
    gyn
    -0.62
    UTERS
    -0.61
    oras
    -0.61
    enment
    -0.61
    POSITIVE LOGITS
     effect
    1.52
     force
    1.22
     law
    1.09
     place
    1.08
     Effect
    0.98
     statute
    0.95
     practice
    0.91
     fruition
    0.91
     existence
    0.91
     practise
    0.83
    Activations Density 0.115%

    No Known Activations