© 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
    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. 7866
    Prev
    Next
    INDEX
    Explanations

    information related to dairy products and their effects on health

    oai_token-act-pair · gpt-3.5-turbo

    topics related to dairy and its impact on health

    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
    ··
    -1.00
     Torch
    -0.92
     Jacksonville
    -0.91
     Jaguars
    -0.90
    VPN
    -0.89
    Blake
    -0.89
    ernand
    -0.88
    Jackson
    -0.86
     Blake
    -0.85
     XCOM
    -0.84
    POSITIVE LOGITS
     milk
    2.23
     dairy
    2.03
     Milk
    2.02
     Dairy
    1.92
    Mil
    1.85
     lact
    1.81
     cheese
    1.75
     cows
    1.73
     yogurt
    1.72
    mil
    1.69
    Activations Density 0.233%

    No Known Activations