Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 22467
    Prev
    Next
    INDEX
    Explanations

    phrases related to illegal wildlife trade, especially in the context of rhino conservation efforts and bat encounters

    oai_token-act-pair · gpt-3.5-turbo

    animal-related terminology and conservation issues

    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
    ij士
    -0.95
    leeve
    -0.82
    İĭ
    -0.78
    isSpecialOrderable
    -0.75
    creen
    -0.74
    Ͻ
    -0.74
    Offline
    -0.74
    ixel
    -0.73
    hiba
    -0.73
    oppable
    -0.72
    POSITIVE LOGITS
     carc
    1.14
     feces
    1.07
     breeding
    1.07
     habitats
    1.07
     colonies
    1.06
    iasis
    1.03
     populations
    1.03
     corpses
    1.02
     sightings
    1.01
     species
    1.01
    Activations Density 0.169%

    No Known Activations