© 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. 11-RES-JB
    11. 14971
    Prev
    Next
    INDEX
    Explanations

    mentions of political candidacy, particularly running for president or other political positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to running for political office

    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
    wolves
    -0.69
    LCS
    -0.69
    vous
    -0.67
    dash
    -0.67
    Zen
    -0.66
    bek
    -0.65
    itional
    -0.64
    agree
    -0.63
    tics
    -0.63
    jing
    -0.63
    POSITIVE LOGITS
     president
    1.40
     reelection
    1.33
     governor
    1.32
     mayor
    1.30
     presidency
    1.26
     office
    1.14
     Presidency
    1.10
     secretary
    1.06
    president
    1.06
     Congress
    1.05
    Activations Density 0.072%

    No Known Activations