© 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. 1571
    Prev
    Next
    INDEX
    Explanations

    mentions of political coalitions and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to political coalitions and party affiliations

    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
    Tang
    -0.90
    SourceFile
    -0.88
    Ô
    -0.86
     Guerrero
    -0.85
    guyen
    -0.84
    ¥µ
    -0.84
     Hawai
    -0.83
    Houston
    -0.81
     Yi
    -0.81
    Hig
    -0.80
    POSITIVE LOGITS
     electorate
    1.16
     Brexit
    1.10
     constituency
    1.10
     scept
    1.05
     Labour
    1.04
     Conservatives
    1.03
     Tories
    1.03
     Ukip
    1.02
     elector
    1.01
     cabinet
    1.01
    Activations Density 0.322%

    No Known Activations