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. 2-RES-JB
    6. 4995
    Prev
    Next
    INDEX
    Explanations

    references to specific types of animals, specifically whales and butterflies

    oai_token-act-pair · gpt-3.5-turbo

    references to marine and avian wildlife, particularly whales and butterflies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rity
    -0.85
    uries
    -0.81
    kaya
    -0.80
    ources
    -0.75
    ettings
    -0.74
    idents
    -0.74
    erenn
    -0.74
    hips
    -0.73
    rogens
    -0.72
    andals
    -0.72
    POSITIVE LOGITS
     hunter
    1.06
    fish
    0.92
     hunts
    0.90
     beetle
    0.89
    ishly
    0.87
     fisher
    0.84
     crab
    0.77
     hunters
    0.77
    asus
    0.76
     farmer
    0.75
    Activations Density 0.075%

    No Known Activations