© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1161
    Prev
    Next
    INDEX
    Explanations

    information related to environmental issues and threats to species and habitats

    oai_token-act-pair · gpt-3.5-turbo

    references to wildlife populations and their conservation status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Elect
    -0.72
    iquid
    -0.71
     Imran
    -0.71
    puter
    -0.70
     accuser
    -0.70
     ELECT
    -0.69
     Tablet
    -0.69
     Phar
    -0.69
     Ghostbusters
    -0.68
    éĹ
    -0.68
    POSITIVE LOGITS
     habitat
    1.72
     breeding
    1.61
     species
    1.58
     extinction
    1.54
    species
    1.53
     extinct
    1.50
     conservation
    1.42
     habitats
    1.40
     biodiversity
    1.39
     wildlife
    1.39
    Activations Density 0.821%

    No Known Activations