© 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. 0-RES-JB
    11. 387
    Prev
    Next
    INDEX
    Explanations

    the word "poke" or variations of it, such as "poked" or "poking."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to playful teasing or making fun of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sovereign
    -0.80
     Rhod
    -0.79
     Montgomery
    -0.78
     Strat
    -0.75
    reshold
    -0.71
     Saturn
    -0.71
     Lords
    -0.70
    uchs
    -0.69
    cale
    -0.69
     Schwarz
    -0.69
    POSITIVE LOGITS
     poke
    2.60
     poked
    2.26
     poking
    2.24
     jab
    1.82
     Poke
    1.53
     peek
    1.47
     prick
    1.43
    PK
    1.26
     smack
    1.20
     puck
    1.17
    Activations Density 0.035%

    No Known Activations