© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1042
    Prev
    Next
    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events or periods of occupation

    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
     HERE
    -0.60
    Thumbnail
    -0.59
     Shutterstock
    -0.58
    /
    -0.58
     inherently
    -0.55
     misconception
    -0.54
     âĢº
    -0.54
    ãĤ¨ãĥ«
    -0.52
     stereotype
    -0.52
     Minion
    -0.52
    POSITIVE LOGITS
     resumed
    0.70
     thereafter
    0.67
    Reloaded
    0.66
     again
    0.64
    ļé
    0.60
    ģ«
    0.60
    bernatorial
    0.60
     postponed
    0.58
    ).[
    0.57
    ixty
    0.57
    Activations Density 2.156%

    No Known Activations