© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4171
    Prev
    Next
    INDEX
    Explanations

    statements related to political actions and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicative of political rhetoric and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç·
    -0.80
    pure
    -0.80
    geist
    -0.79
     tremend
    -0.78
    upe
    -0.77
    fuck
    -0.75
    gru
    -0.73
    lol
    -0.73
    greg
    -0.73
    ileged
    -0.73
    POSITIVE LOGITS
     lawmakers
    1.22
     MPs
    1.12
     Treasury
    1.10
     President
    1.10
     campaigners
    1.09
     Congress
    1.09
     diplomats
    1.05
     Attorney
    1.05
     negotiators
    1.05
     officials
    1.05
    Activations Density 0.717%

    No Known Activations