© 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. 4-RES-JB
    11. 5089
    Prev
    Next
    INDEX
    Explanations

    references to cigarettes and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cigarettes and their related products

    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
    */(
    -0.78
    herty
    -0.77
    isite
    -0.73
    pmwiki
    -0.72
    oral
    -0.70
    icter
    -0.70
    yss
    -0.70
    UFC
    -0.69
    variable
    -0.67
    ede
    -0.67
    POSITIVE LOGITS
    arette
    1.34
    arettes
    1.24
     cigarettes
    1.19
     smoking
    1.13
     smokers
    1.10
     cigarette
    1.08
     smoker
    1.08
     cig
    1.06
     smoked
    0.97
    cigarettes
    0.95
    Activations Density 0.009%

    No Known Activations