© 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. 21166
    Prev
    Next
    INDEX
    Explanations

    terms related to urban environments and street activities

    oai_token-act-pair · gpt-3.5-turbo

    references to streets and street-related concepts

    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
    insula
    -0.72
    ynt
    -0.68
    uary
    -0.64
    IUM
    -0.62
    ï¸ı
    -0.62
    enza
    -0.61
    kaya
    -0.61
     downstream
    -0.60
     Seas
    -0.60
    hetical
    -0.60
    POSITIVE LOGITS
    hog
    0.88
     closures
    0.82
     hopping
    0.79
     dwell
    0.79
    clean
    0.77
    busters
    0.77
    pain
    0.75
    tri
    0.74
    jump
    0.74
    walker
    0.72
    Activations Density 0.215%

    No Known Activations