© 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. 21095
    Prev
    Next
    INDEX
    Explanations

    names of places and specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or organizations

    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
    erker
    -0.76
    taker
    -0.75
    Ó
    -0.73
    bler
    -0.72
    blogs
    -0.72
    picking
    -0.70
    maxwell
    -0.70
    Discuss
    -0.70
    Putin
    -0.70
    sheet
    -0.68
    POSITIVE LOGITS
    ño
    1.40
    ña
    1.35
     del
    1.25
    ÃŃa
    1.24
    ón
    1.22
     Mex
    1.21
    ñ
    1.20
     Grande
    1.18
     dos
    1.17
     Portug
    1.16
    Activations Density 0.240%

    No Known Activations