© 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. 6-RES-JB
    11. 21752
    Prev
    Next
    INDEX
    Explanations

    words related to smells or odors

    oai_token-act-pair · gpt-3.5-turbo

    instances of "smirk" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.84
    hyde
    -0.80
     Scrib
    -0.68
    Letter
    -0.66
     Emir
    -0.66
    PORT
    -0.63
    Plex
    -0.62
     Yugoslav
    -0.61
    UFC
    -0.61
     Governors
    -0.61
    POSITIVE LOGITS
    ithing
    1.06
    acking
    1.05
    attering
    1.05
    ould
    1.03
    itten
    1.03
    eared
    0.98
    oky
    0.97
    ashed
    0.97
    udge
    0.95
    ashing
    0.94
    Activations Density 0.015%

    No Known Activations