© 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. 0-RES-JB
    11. 11399
    Prev
    Next
    INDEX
    Explanations

    thumbs-related phrases like "thumbs up" and "thumbs down"

    oai_token-act-pair · gpt-3.5-turbo

    references to gestures of approval or disapproval, specifically "thumbs up" and "thumbs down."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Invasion
    -0.70
     Tale
    -0.69
    £ı
    -0.68
    enario
    -0.68
    lain
    -0.65
    anny
    -0.65
    arian
    -0.63
     sheltered
    -0.63
     tracing
    -0.63
    olate
    -0.63
    POSITIVE LOGITS
     thumbs
    3.92
    umbs
    1.61
     cheers
    1.36
     majorities
    0.94
     disabilities
    0.92
     enthusiastic
    0.89
     smiles
    0.89
    votes
    0.86
     nods
    0.85
     congr
    0.83
    Activations Density 0.034%

    No Known Activations