© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16278
    Prev
    Next
    INDEX
    Explanations

    mentions of shops or items related to shopping

    oai_token-act-pair · gpt-3.5-turbo

    references to retail shops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thia
    -0.76
    theless
    -0.67
     accur
    -0.65
     Marketable
    -0.63
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.61
    SPONSORED
    -0.61
     staggered
    -0.61
    ioxide
    -0.61
     Buckley
    -0.61
     Rockefeller
    -0.61
    POSITIVE LOGITS
    keepers
    1.20
    keeper
    1.20
    lifting
    1.12
    shop
    1.08
     shop
    1.05
    andise
    1.01
    worn
    0.96
    ify
    0.92
     shops
    0.89
    keep
    0.88
    Activations Density 0.015%

    No Known Activations