© 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. 2370
    Prev
    Next
    INDEX
    Explanations

    code snippets related to database migration and programming functions

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

    programming keywords related to visibility and access in code

    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
    oux
    -0.77
    umbn
    -0.70
    scl
    -0.68
     Canad
    -0.66
    uga
    -0.65
    uit
    -0.65
    bourg
    -0.65
    ophy
    -0.65
    usc
    -0.65
    ologies
    -0.64
    POSITIVE LOGITS
     static
    1.11
     override
    0.97
     void
    0.96
     boolean
    0.94
     async
    0.93
     enum
    0.90
     bool
    0.87
    Widget
    0.80
     interface
    0.78
    olean
    0.77
    Activations Density 0.031%

    No Known Activations