© 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. 3-RES-JB
    11. 1865
    Prev
    Next
    INDEX
    Explanations

    specific mentions of politicians and political events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "Sen." followed by various names, indicating references to senators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chwitz
    -0.77
    ¥ŀ
    -0.72
    zsche
    -0.72
    zn
    -0.71
     guiActiveUn
    -0.70
    ritis
    -0.70
    idious
    -0.69
    uner
    -0.67
    inarily
    -0.67
    ffen
    -0.66
    POSITIVE LOGITS
     Majority
    0.92
     Olympia
    0.75
     Flake
    0.73
     Senators
    0.71
     Appropriations
    0.71
     Louie
    0.70
    wikipedia
    0.69
     Citizens
    0.68
     Standing
    0.68
     Ridge
    0.68
    Activations Density 0.101%

    No Known Activations