© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 10258
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of animals, specifically goats and donkeys, as well as specific names like "Paula"

    oai_token-act-pair · gpt-3.5-turbo

    references to goats and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orneys
    -0.78
    ept
    -0.69
    cknowled
    -0.68
     Barnett
    -0.67
    hips
    -0.67
    aneously
    -0.65
    urrent
    -0.65
     stresses
    -0.65
    eering
    -0.63
    nant
    -0.63
    POSITIVE LOGITS
     goat
    1.13
     goats
    1.06
     Cheese
    1.05
     Goat
    1.03
    asus
    0.94
     cheese
    0.94
    qv
    0.83
    wright
    0.76
    weed
    0.75
    ghan
    0.72
    Activations Density 0.007%

    No Known Activations