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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 24359
    Prev
    Next
    INDEX
    Explanations

    animal-related terms and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to animal welfare and rights

    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
    heit
    -0.79
    unda
    -0.76
    creen
    -0.76
    hips
    -0.70
    lain
    -0.69
    outer
    -0.69
    gren
    -0.68
    uden
    -0.68
     Sutherland
    -0.65
    chool
    -0.65
    POSITIVE LOGITS
     cruelty
    1.13
     welf
    1.07
     kingdom
    1.04
     welfare
    1.02
     carc
    1.02
     Welfare
    0.98
     Cruel
    0.97
     domest
    0.96
    arium
    0.96
     species
    0.91
    Activations Density 0.057%

    No Known Activations