© 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. 1483
    Prev
    Next
    INDEX
    Explanations

    the word "those" followed by a numerical value, such as "9" or "10"

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases focused on the word "those."

    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
    achus
    -0.80
    ILY
    -0.77
    kamp
    -0.76
    ob
    -0.76
    ario
    -0.70
    onis
    -0.69
    shapeshifter
    -0.68
     Shutterstock
    -0.65
    orate
    -0.64
     Ness
    -0.63
    POSITIVE LOGITS
     pesky
    1.15
     kinds
    1.04
     sorts
    0.93
     same
    0.78
     fateful
    0.78
     types
    0.77
     thoughts
    0.76
     facts
    0.75
     sights
    0.75
     feelings
    0.73
    Activations Density 0.067%

    No Known Activations