© 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. 11-RES-JB
    11. 12461
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    references to political discussions and legislative actions

    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
     worldwide
    -0.78
    sterdam
    -0.78
     Ft
    -0.77
    Miami
    -0.70
    icide
    -0.68
     civilizations
    -0.67
     Worldwide
    -0.67
     Hispan
    -0.66
     fortun
    -0.66
     armor
    -0.65
    POSITIVE LOGITS
     Opposition
    1.68
     NDP
    1.64
     Liberals
    1.59
     Liberal
    1.59
     ALP
    1.52
     Labor
    1.48
     Treasurer
    1.48
    Liberal
    1.45
    Labor
    1.41
     Mulcair
    1.39
    Activations Density 0.729%

    No Known Activations