© 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. 13885
    Prev
    Next
    INDEX
    Explanations

    names of individuals, potentially related to a cast or production team

    oai_token-act-pair · gpt-3.5-turbo

    names of cast and crew members in film or television

    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
    ccording
    -0.66
    shows
    -0.61
     portals
    -0.61
     necessities
    -0.60
    products
    -0.60
     entails
    -0.59
     VIDEOS
    -0.59
     suppose
    -0.57
     implies
    -0.57
     underestimated
    -0.56
    POSITIVE LOGITS
     Jr
    1.29
    owicz
    1.04
     Sr
    0.96
     III
    0.94
    hetti
    0.89
    son
    0.88
    kamp
    0.87
    kson
    0.87
    ovich
    0.87
    meyer
    0.86
    Activations Density 0.248%

    No Known Activations