© 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. 0-RES-JB
    11. 17959
    Prev
    Next
    INDEX
    Explanations

    government-related terms or mentions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government officials or references to government

    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
     liver
    -0.65
     promotion
    -0.65
     prepar
    -0.63
     endurance
    -0.63
     adapted
    -0.63
     onion
    -0.62
     preparation
    -0.62
     adaptation
    -0.61
     modification
    -0.61
     Minor
    -0.61
    POSITIVE LOGITS
    Gov
    4.22
    gov
    1.62
    Govern
    1.42
    Politics
    1.28
    govtrack
    1.23
    Senate
    1.23
    Mayor
    1.18
    Government
    1.17
    Polit
    1.16
    Senator
    1.09
    Activations Density 0.014%

    No Known Activations