© 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. 10-RES-JB
    11. 780
    Prev
    Next
    INDEX
    Explanations

    words related to legislative processes and political activities

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bills and their sponsorship status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.74
     Notting
    -0.64
    é¾įåĸļ士
    -0.64
    trained
    -0.63
    ÃĽ
    -0.63
     Ubisoft
    -0.63
     fortun
    -0.62
    naissance
    -0.62
     Pax
    -0.61
    NK
    -0.61
    POSITIVE LOGITS
    ospons
    1.60
    osponsors
    1.54
    Senate
    1.46
     amendments
    1.45
     Senate
    1.44
     legislation
    1.43
     bipartisan
    1.42
     bill
    1.41
     repeal
    1.39
     Legislation
    1.38
    Activations Density 1.219%

    No Known Activations