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. 0-RES-JB
    6. 109
    Prev
    Next
    INDEX
    Explanations

    animal-related words, specifically focusing on goats, donkeys, and camels

    oai_token-act-pair · gpt-3.5-turbo

    references to goats and related animals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifest
    -0.73
     Lynd
    -0.72
    itutional
    -0.70
    font
    -0.68
     Tray
    -0.67
    Const
    -0.67
    idents
    -0.67
    VOL
    -0.64
     McC
    -0.64
     Martial
    -0.63
    POSITIVE LOGITS
     goat
    3.72
     goats
    3.51
     Goat
    2.72
     donkey
    2.23
     sheep
    1.73
     camel
    1.58
     cows
    1.56
     lamb
    1.44
     Sheep
    1.43
     shepherd
    1.41
    Activations Density 0.033%

    No Known Activations