© 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. 3971
    Prev
    Next
    INDEX
    Explanations

    descriptions of outdoor scenes and actions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to movement or physical descriptions in a narrative

    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
    ģĸ
    -0.59
     incent
    -0.57
    Asset
    -0.57
     Nationwide
    -0.55
    quickShipAvailable
    -0.55
    wcs
    -0.54
     citiz
    -0.54
     Insider
    -0.50
    externalActionCode
    -0.50
    nces
    -0.49
    POSITIVE LOGITS
     paw
    0.59
     boulder
    0.58
    atche
    0.57
     stairs
    0.56
     Weasley
    0.54
     luggage
    0.50
    stairs
    0.50
    buck
    0.49
     gigg
    0.49
     orbit
    0.49
    Activations Density 4.621%

    No Known Activations