© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5092
    Prev
    Next
    INDEX
    Explanations

    positive sentiments or outcomes

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    expressions of positivity or positive sentiments in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Boko
    -0.65
     trailing
    -0.57
     Lucia
    -0.57
     Merkel
    -0.55
     Haram
    -0.54
     Werewolf
    -0.53
     spo
    -0.53
     emer
    -0.51
     STEP
    -0.51
     Brilliant
    -0.51
    POSITIVE LOGITS
    itivity
    1.56
    itional
    1.52
    itions
    1.49
    itiveness
    1.33
    icion
    1.26
    itionally
    1.22
    ited
    1.22
    itor
    1.22
    itives
    1.21
    ibilities
    1.21
    Activations Density 0.060%

    No Known Activations