© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5033
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to Rush Limbaugh

    oai_token-act-pair · gpt-3.5-turbo

    references to the media personality Rush Limbaugh

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.71
     concess
    -0.68
     FANT
    -0.65
    displayText
    -0.63
     salsa
    -0.63
     bom
    -0.63
     tender
    -0.62
     reson
    -0.61
    worldly
    -0.60
     MFT
    -0.60
    POSITIVE LOGITS
     Limbaugh
    1.36
    die
    1.18
    cliffe
    1.03
    away
    0.89
     Hour
    0.86
    more
    0.86
    ton
    0.85
    jet
    0.82
    anism
    0.81
     Rush
    0.81
    Activations Density 0.046%

    No Known Activations