© 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. 2753
    Prev
    Next
    INDEX
    Explanations

    information related to wildlife conservation organizations and research studies on wildlife populations

    oai_token-act-pair · gpt-3.5-turbo

    references to conservation organizations and their activities

    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
    ettings
    -0.81
    furt
    -0.77
    hemy
    -0.75
    ipolar
    -0.70
    ilege
    -0.69
     kne
    -0.67
     earners
    -0.67
     bricks
    -0.66
    rises
    -0.65
    bleacher
    -0.65
    POSITIVE LOGITS
     Wildlife
    2.00
     wildlife
    1.73
     Conservation
    1.67
     Fisheries
    1.61
     biologists
    1.60
     biologist
    1.60
     Species
    1.56
     conservation
    1.54
     Veterinary
    1.52
     Forestry
    1.49
    Activations Density 0.494%

    No Known Activations