© 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. 8-RES-JB
    11. 19336
    Prev
    Next
    INDEX
    Explanations

    text related to political elections, candidates, and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political elections and candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apologise
    -1.00
    obyl
    -0.98
    âĹ¼
    -0.97
    utical
    -0.84
    ĸļ
    -0.81
     Neuroscience
    -0.78
    sterdam
    -0.78
     explorers
    -0.77
     apologised
    -0.76
     enqu
    -0.73
    POSITIVE LOGITS
     turnout
    1.47
     voters
    1.40
     voter
    1.39
    Republican
    1.37
     polling
    1.35
     Republican
    1.35
    Democrats
    1.35
     polls
    1.35
     caucus
    1.34
     Democratic
    1.34
    Activations Density 1.015%

    No Known Activations