© 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. 3-RES-JB
    11. 614
    Prev
    Next
    INDEX
    Explanations

    mentions of bikers

    oai_token-act-pair · gpt-3.5-turbo

    words related to biking or cyclists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plain
    -0.75
    urer
    -0.71
    period
    -0.69
    win
    -0.66
    bright
    -0.66
    argon
    -0.64
    onso
    -0.64
     miscarriage
    -0.63
    plin
    -0.63
    nah
    -0.63
    POSITIVE LOGITS
    iking
    1.06
     biking
    1.03
    iker
    1.02
    ikers
    1.01
    bike
    0.95
     Bike
    0.92
     gangs
    0.79
     bike
    0.78
     Helmet
    0.77
     Riders
    0.77
    Activations Density 0.011%

    No Known Activations