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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20733
    Prev
    Next
    INDEX
    Explanations

    keywords related to bicycles or bike-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to bicycles and biking infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arial
    -0.80
     Solitaire
    -0.79
     Seym
    -0.78
    ordial
    -0.77
    uminati
    -0.75
     Jehovah
    -0.71
     uranium
    -0.71
    naires
    -0.70
    ember
    -0.70
    esson
    -0.67
    POSITIVE LOGITS
    bike
    1.10
     rider
    1.08
     commuting
    1.06
    packing
    1.04
     riders
    1.03
    cling
    1.01
     lanes
    1.00
     commuters
    0.99
     commuter
    0.97
     messenger
    0.97
    Activations Density 0.062%

    No Known Activations