© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8047
    Prev
    Next
    INDEX
    Explanations

    terms related to smoking cigarettes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "smoking" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Horizons
    -0.76
    Grid
    -0.75
     Vector
    -0.68
    Helper
    -0.65
    olit
    -0.65
    aga
    -0.64
     Convert
    -0.64
    DF
    -0.64
    Gener
    -0.64
     Scale
    -0.64
    POSITIVE LOGITS
     smoking
    3.79
    smoking
    3.27
     Smoking
    2.79
     smokers
    1.96
     smoker
    1.95
     vaping
    1.94
     cigarette
    1.91
     smokes
    1.91
     cigarettes
    1.88
     tobacco
    1.88
    Activations Density 0.007%

    No Known Activations