© 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. 11-RES-JB
    11. 5915
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude or thanks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and acknowledgment of contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.73
    OULD
    -0.66
     lacks
    -0.65
     stalled
    -0.64
     grapple
    -0.63
     revolves
    -0.63
    SPONSORED
    -0.63
     confront
    -0.63
     occurs
    -0.62
     nonexistent
    -0.61
    POSITIVE LOGITS
    ortium
    0.89
     who
    0.86
    !!
    0.85
    who
    0.84
     for
    0.81
    !!!!
    0.80
    !!!
    0.78
    !
    0.77
     :)
    0.76
     THANK
    0.75
    Activations Density 0.234%

    No Known Activations