© 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. 10-RES-JB
    11. 3006
    Prev
    Next
    INDEX
    Explanations

    mentions of smoking

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "smoke" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lama
    -0.64
     MacArthur
    -0.62
     quo
    -0.61
     Xavier
    -0.60
    rants
    -0.59
     headaches
    -0.58
    thus
    -0.57
     Graphics
    -0.57
     Veterans
    -0.56
     unmarked
    -0.56
    POSITIVE LOGITS
    iley
    1.45
    ooth
    1.42
    oky
    1.31
    ugg
    1.28
    okers
    1.28
    itten
    1.25
    oker
    1.24
    oking
    1.23
    okes
    1.21
    okin
    1.21
    Activations Density 0.013%

    No Known Activations