© 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. 8-RES-JB
    11. 22312
    Prev
    Next
    INDEX
    Explanations

    the word "smoky" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to "sm" or "smoking" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.75
     pleas
    -0.71
     Emir
    -0.66
     Vanguard
    -0.62
     monarch
    -0.60
     Syl
    -0.60
    Letter
    -0.59
    uate
    -0.59
     Scrib
    -0.59
     Masters
    -0.58
    POSITIVE LOGITS
    attering
    1.29
    itten
    1.23
    oky
    1.22
    ugg
    1.19
    udge
    1.15
    ithing
    1.12
    ashing
    1.11
    acking
    1.08
    acks
    1.07
    iley
    1.07
    Activations Density 0.014%

    No Known Activations