© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 5375
    Prev
    Next
    INDEX
    Explanations

    mentions of smoke

    oai_token-act-pair · gpt-3.5-turbo

    references to smoke

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":["
    -0.70
    ngth
    -0.67
    rity
    -0.66
    amily
    -0.64
    uate
    -0.63
    apter
    -0.63
     Vanguard
    -0.62
     Volt
    -0.62
    INAL
    -0.62
    ITIES
    -0.61
    POSITIVE LOGITS
    creen
    1.08
     cessation
    0.97
     inhal
    0.91
    cone
    0.84
    crow
    0.84
    guns
    0.83
    gun
    0.82
    balls
    0.81
     smoke
    0.81
    ying
    0.81
    Activations Density 0.042%

    No Known Activations