© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1323
    Prev
    Next
    INDEX
    Explanations

    highly descriptive terms related to politics and individuals involved in political activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to divisive political 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
     Simulator
    -0.83
    eria
    -0.74
    é¾įåĸļ士
    -0.73
    crow
    -0.73
    ercise
    -0.71
    ruction
    -0.71
    atown
    -0.70
    mage
    -0.70
    ossession
    -0.69
    anguage
    -0.69
    POSITIVE LOGITS
     presidents
    1.39
     personalities
    1.39
     secretaries
    1.38
     politicians
    1.36
     ambassadors
    1.34
     nominees
    1.33
     leaders
    1.32
     advisers
    1.31
     figures
    1.31
     celebrities
    1.30
    Activations Density 0.359%

    No Known Activations