© 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. 10-RES-JB
    11. 11624
    Prev
    Next
    INDEX
    Explanations

    mentions of buying or acquiring different items or products

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to purchasing and consumer behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aucuses
    -0.76
    vae
    -0.75
    population
    -0.74
    oxicity
    -0.71
    athi
    -0.70
    seen
    -0.69
    xual
    -0.69
    thumbnails
    -0.67
    Tip
    -0.67
    pmwiki
    -0.67
    POSITIVE LOGITS
     groceries
    1.14
     cheapest
    1.10
     pricey
    1.06
     cheaper
    1.03
     cheap
    1.02
     tickets
    1.01
     cheaply
    1.00
     expensive
    1.00
     discounted
    0.99
     subscription
    0.92
    Activations Density 0.239%

    No Known Activations