© 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. 9-RES-JB
    11. 11416
    Prev
    Next
    INDEX
    Explanations

    promotional offers and discounts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating promotional offers or free services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hya
    -0.72
    aceutical
    -0.68
    igl
    -0.67
     threaten
    -0.65
    hall
    -0.64
    Occup
    -0.64
     overwhel
    -0.63
     threatens
    -0.62
    wikipedia
    -0.61
    bell
    -0.60
    POSITIVE LOGITS
     sale
    0.95
     purchase
    0.91
     beginners
    0.90
     everyone
    0.90
     Adults
    0.88
     ages
    0.86
    got
    0.86
     subscribers
    0.84
     anyone
    0.84
     FREE
    0.83
    Activations Density 0.155%

    No Known Activations