© 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. 2-RES-JB
    11. 12640
    Prev
    Next
    INDEX
    Explanations

    mentions of the political party "Democrats"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Democratic Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.83
    orical
    -0.78
    fleet
    -0.74
    asus
    -0.74
    obar
    -0.72
    antly
    -0.71
    inventoryQuantity
    -0.69
    thur
    -0.69
     Harrington
    -0.69
    --+
    -0.69
    POSITIVE LOGITS
     Democrats
    0.83
     Party
    0.81
    Democrats
    0.81
     turnout
    0.73
     strongh
    0.73
     operatives
    0.69
     strugg
    0.68
     Caucus
    0.68
     insiders
    0.67
     republic
    0.67
    Activations Density 0.015%

    No Known Activations