© 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. 3553
    Prev
    Next
    INDEX
    Explanations

    mentions of educational or research institutions specializing in astronomy and history

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

    institutional affiliations or references related to academic or scientific organizations

    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
    ought
    -0.84
    worms
    -0.75
    iddler
    -0.73
    kered
    -0.72
    abbit
    -0.72
    calling
    -0.72
    arted
    -0.71
    lessly
    -0.70
    oshenko
    -0.70
    augh
    -0.70
    POSITIVE LOGITS
     Democr
    1.29
     Univers
    1.22
     Indust
    1.22
     Polit
    1.21
     Instit
    1.16
     Agric
    1.14
     Econom
    1.13
     Intern
    1.12
     Portug
    1.10
     Libre
    1.09
    Activations Density 0.214%

    No Known Activations