© 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. 9-RES-JB
    11. 4288
    Prev
    Next
    INDEX
    Explanations

    phrases indicating announcements or declarations of pleasure or happiness

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 9 - joy

    No Comments

    Negative Logits
     comprehension
    -0.72
    ById
    -0.71
    anooga
    -0.68
     aversion
    -0.66
    soDeliveryDate
    -0.65
    puted
    -0.61
    VERTISEMENT
    -0.59
     Wise
    -0.58
    rarily
    -0.56
     subur
    -0.55
    POSITIVE LOGITS
     announce
    1.39
     introduce
    1.08
     hear
    1.07
     endorse
    1.01
     welcome
    1.00
     invite
    0.99
     see
    0.98
     unveil
    0.97
     join
    0.96
     participate
    0.95
    Activations Density 0.073%

    No Known Activations