© 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. 22353
    Prev
    Next
    INDEX
    Explanations

    healthcare-related terms or departments within ministries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health and government ministries

    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
     Thoughts
    -0.78
    Ô
    -0.75
     Theory
    -0.74
     Members
    -0.74
     Steal
    -0.74
    ®,
    -0.73
    Spread
    -0.73
     Travels
    -0.72
     Stories
    -0.72
     Locations
    -0.71
    POSITIVE LOGITS
     ministry
    1.59
     bureau
    1.47
     department
    1.45
     committee
    1.38
     regulator
    1.37
     watchdog
    1.37
     commissioner
    1.35
     minister
    1.29
     tribunal
    1.26
     commission
    1.25
    Activations Density 0.272%

    No Known Activations