© 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. 12-RES-JB
    11. 4671
    Prev
    Next
    INDEX
    Explanations

    details related to a stadium renovation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    discussions related to governance and legislative matters

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Ruby
    -1.20
     Ruby
    -1.08
     Copenhagen
    -0.97
     Haf
    -0.96
    Weiss
    -0.94
    Nar
    -0.93
     ruby
    -0.88
     sharks
    -0.87
    æ
    -0.87
    deen
    -0.86
    POSITIVE LOGITS
     Indiana
    2.37
    Indiana
    2.32
     Indianapolis
    2.20
     Indy
    2.12
     IU
    2.03
     Pence
    2.02
     Pacers
    1.78
     Purdue
    1.66
     Blooming
    1.58
     Colts
    1.54
    Activations Density 0.348%

    No Known Activations