© 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. 12232
    Prev
    Next
    INDEX
    Explanations

    button-related terms or references in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to buttons in various contexts

    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
    study
    -0.80
     Foster
    -0.72
    ertation
    -0.70
    ilic
    -0.70
    orous
    -0.66
    aith
    -0.64
     Piper
    -0.63
    idis
    -0.63
     retrospective
    -0.62
    Prem
    -0.61
    POSITIVE LOGITS
     buttons
    4.01
     button
    2.50
    button
    2.10
     Button
    2.00
    Button
    1.74
     levers
    1.52
     menus
    1.49
     icons
    1.43
     badges
    1.43
     pins
    1.40
    Activations Density 0.016%

    No Known Activations