© 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. 12479
    Prev
    Next
    INDEX
    Explanations

    a variety of animals, especially those related to farms or dangerous wildlife

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of animals, particularly those related to harmful or dangerous interactions

    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
     Investor
    -0.84
    essional
    -0.75
    inventoryQuantity
    -0.75
    imilation
    -0.73
    ihad
    -0.70
    ilon
    -0.70
     Ending
    -0.69
    igmatic
    -0.69
     Candidate
    -0.69
    href
    -0.68
    POSITIVE LOGITS
     rabbits
    1.66
     goats
    1.54
     reptiles
    1.52
     rodents
    1.44
     dolphins
    1.44
     turtles
    1.43
     pige
    1.43
     squirrel
    1.42
     mammals
    1.42
     horses
    1.41
    Activations Density 0.132%

    No Known Activations