© 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. 10-RES-JB
    11. 16533
    Prev
    Next
    INDEX
    Explanations

    mentions of conservative political commentators, specifically Rush Limbaugh and Sean Hannity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent conservative media figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    binding
    -0.82
    cles
    -0.67
    export
    -0.66
    yards
    -0.65
     Cyprus
    -0.64
     solitary
    -0.63
    activation
    -0.63
    memory
    -0.63
     scarce
    -0.63
    conservancy
    -0.62
    POSITIVE LOGITS
     aired
    1.14
     Hannity
    1.14
     airs
    1.07
     Tonight
    1.06
     airing
    1.02
    CNN
    0.98
     comedians
    0.91
     Live
    0.88
     MSNBC
    0.87
     interviewer
    0.87
    Activations Density 0.130%

    No Known Activations