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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 17127
    Prev
    Next
    INDEX
    Explanations

    mentions of smoking-related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to guidance and assistance in decision-making, particularly concerning tobacco use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylum
    -0.93
     Klingon
    -0.90
     Ellison
    -0.87
     Assy
    -0.87
    ajor
    -0.87
     Ramsey
    -0.87
    yss
    -0.85
     ransom
    -0.84
    maid
    -0.84
     Spartans
    -0.83
    POSITIVE LOGITS
     nicotine
    2.20
     smokers
    2.19
     cig
    2.18
     tobacco
    2.12
     Nicotine
    2.12
     smoker
    2.11
     cigarette
    2.09
     cigarettes
    2.09
     smoking
    2.09
     vaping
    2.08
    Activations Density 0.294%

    No Known Activations