© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2448
    Prev
    Next
    INDEX
    Explanations

    phrases related to riding a bike

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to biking and riding activities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ascript
    -0.75
    arial
    -0.70
    elman
    -0.70
    ifiers
    -0.69
    dated
    -0.65
    essment
    -0.64
    azing
    -0.64
    uese
    -0.63
    ening
    -0.61
    ples
    -0.61
    POSITIVE LOGITS
    hare
    1.07
     bikes
    1.03
     bicycles
    1.00
     shotgun
    1.00
     motorcycles
    0.95
    along
    0.95
    ousel
    0.90
     coaster
    0.89
     horses
    0.89
    bike
    0.83
    Activations Density 0.077%

    No Known Activations