© 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. 1184
    Prev
    Next
    INDEX
    Explanations

    politicians' names, particularly Senator Bob Corker

    oai_token-act-pair · gpt-3.5-turbo

    names of senators and congressional figures

    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
    DragonMagazine
    -0.85
     unequ
    -0.69
    ebook
    -0.68
    ateurs
    -0.62
     brim
    -0.62
     Pyramid
    -0.60
    ilion
    -0.60
     emanc
    -0.60
    estones
    -0.59
    Reviewer
    -0.58
    POSITIVE LOGITS
     filibuster
    1.07
     senators
    1.04
     Grassley
    1.02
     Corker
    1.02
     filib
    1.02
    Senator
    0.95
     Schumer
    0.94
     Stab
    0.89
    Sen
    0.88
     Blumenthal
    0.87
    Activations Density 0.076%

    No Known Activations