© 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. 2284
    Prev
    Next
    INDEX
    Explanations

    information related to wildlife and ecosystems

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

    terms related to endangered species and their ecological importance

    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
     Fiat
    -0.80
     blasphemy
    -0.78
     Rouhani
    -0.75
     Netanyahu
    -0.71
     Indy
    -0.70
     Machine
    -0.70
    TeX
    -0.69
     Wiz
    -0.68
     Moment
    -0.68
     Miliband
    -0.68
    POSITIVE LOGITS
     habitat
    1.48
    species
    1.38
     habitats
    1.34
     herds
    1.31
     nesting
    1.30
     nests
    1.26
     breeding
    1.25
     species
    1.20
     mating
    1.20
     grazing
    1.19
    Activations Density 0.586%

    No Known Activations