© 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. 4-RES-JB
    11. 20059
    Prev
    Next
    INDEX
    Explanations

    keywords related to tobacco and smoking

    oai_token-act-pair · gpt-3.5-turbo

    mentions of tobacco and its related products or issues

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

    No Comments

    Negative Logits
     Wynne
    -0.76
    imov
    -0.72
     Ake
    -0.71
    variable
    -0.71
     Defenders
    -0.69
    ithmetic
    -0.66
     Lazarus
    -0.66
    infeld
    -0.65
    alon
    -0.63
    irlf
    -0.63
    POSITIVE LOGITS
     cigarettes
    1.10
     smoking
    1.03
     smoke
    0.94
     tobacco
    0.94
     cessation
    0.93
     cigarette
    0.91
    arette
    0.84
    acco
    0.84
     cig
    0.83
     smokers
    0.83
    Activations Density 0.012%

    No Known Activations