© 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. 8-RES-JB
    11. 23710
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific objects or products, particularly related to food and beverages

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and items, particularly those related to food, objects, and tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DPR
    -0.74
     Territories
    -0.63
     UNCLASSIFIED
    -0.61
     Democr
    -0.60
     Innocent
    -0.60
    Demand
    -0.59
     Definitive
    -0.58
    Ĭ±
    -0.58
     Marketable
    -0.58
     Darkness
    -0.57
    POSITIVE LOGITS
    works
    0.89
    less
    0.85
    maker
    0.84
    hog
    0.84
    hook
    0.83
    worker
    0.80
    box
    0.78
    washer
    0.77
    packing
    0.77
    bag
    0.76
    Activations Density 0.721%

    No Known Activations