© 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. 2-RES-JB
    11. 17679
    Prev
    Next
    INDEX
    Explanations

    devices or activities related to smoking

    oai_token-act-pair · gpt-3.5-turbo

    references to smoking and tobacco-related items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ü
    -0.79
    âķIJâķIJ
    -0.73
    姫
    -0.70
     MacDonald
    -0.70
    yss
    -0.67
    UTERS
    -0.67
    Ó
    -0.67
     Livingston
    -0.67
    tics
    -0.67
     Holt
    -0.65
    POSITIVE LOGITS
     cigar
    1.17
     cigars
    1.09
    illo
    0.99
     wrapper
    0.95
    arette
    0.88
    uana
    0.80
     smoked
    0.78
    ango
    0.76
    rador
    0.76
     Cig
    0.75
    Activations Density 0.004%

    No Known Activations