© 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. 2777
    Prev
    Next
    INDEX
    Explanations

    words related to medical procedures or scientific figures

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific symbols or characters that seem irregular or non-standard in the text

    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
     metic
    -0.99
     CAS
    -0.78
     ANGEL
    -0.77
     SUN
    -0.75
     SIM
    -0.73
     CY
    -0.73
     AS
    -0.73
     ROS
    -0.72
     JPM
    -0.71
     COM
    -0.70
    POSITIVE LOGITS
    c
    1.74
    d
    1.67
    b
    1.66
    h
    1.62
    p
    1.62
    r
    1.59
    f
    1.58
    e
    1.55
    sb
    1.53
    t
    1.50
    Activations Density 0.195%

    No Known Activations