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

    Neuronpedia

    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. 1-RES-JB
    11. 20285
    Prev
    Next
    INDEX
    Explanations

    words related to debates

    oai_token-act-pair · gpt-3.5-turbo

    discussions and mentions of debates on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    printed
    -0.72
    ever
    -0.71
    alty
    -0.70
    eared
    -0.68
    jer
    -0.66
    veh
    -0.65
    uilt
    -0.65
     liner
    -0.64
    resp
    -0.64
    zer
    -0.64
    POSITIVE LOGITS
     debate
    1.15
     debates
    1.08
     Debate
    0.97
     debating
    0.92
     debated
    0.85
    halla
    0.83
     moderators
    0.78
     forum
    0.73
     discussion
    0.71
     controversy
    0.70
    Activations Density 0.014%

    No Known Activations