© 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. 12545
    Prev
    Next
    INDEX
    Explanations

    words related to smoking or smoking-related activities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "smoke" or related terms

    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
     Cerberus
    -0.66
    TAIN
    -0.65
     Vanguard
    -0.65
    DragonMagazine
    -0.64
    EMENT
    -0.63
    RELATED
    -0.62
    ARDIS
    -0.61
     Welsh
    -0.61
     Lyme
    -0.61
    ITAL
    -0.60
    POSITIVE LOGITS
    ooth
    1.33
    oke
    1.13
    oky
    1.12
    oking
    1.08
    ugg
    1.05
    attering
    1.02
    okes
    1.00
    itten
    1.00
    oked
    0.99
    ould
    0.97
    Activations Density 0.004%

    No Known Activations