© 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. 11-RES-JB
    11. 6815
    Prev
    Next
    INDEX
    Explanations

    phrases related to political elections and candidates

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their associated contexts in political discussions

    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
     interchange
    -0.82
     censored
    -0.81
     interoper
    -0.80
     liner
    -0.79
    obyl
    -0.79
     forb
    -0.78
     confiscated
    -0.76
     curator
    -0.76
    assetsadobe
    -0.75
     censor
    -0.73
    POSITIVE LOGITS
    Democrats
    1.87
    Republicans
    1.70
     Voters
    1.68
    Republican
    1.67
    Democratic
    1.64
    Poll
    1.49
     Election
    1.47
    Clinton
    1.45
    Romney
    1.45
     Voter
    1.44
    Activations Density 0.390%

    No Known Activations