© 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 EvalsExportsAPI 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. 14984
    Prev
    Next
    INDEX
    Explanations

    various health-related terms and phrases, including medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    aspects related to activities, practices, and engagement in various tasks

    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
     censored
    -0.96
     eleph
    -0.94
     seized
    -0.89
     oun
    -0.89
     unspecified
    -0.87
     exiled
    -0.81
     outgoing
    -0.81
     committed
    -0.80
     earthqu
    -0.80
     contested
    -0.78
    POSITIVE LOGITS
    Avoid
    1.78
    Tips
    1.77
    Types
    1.73
    Learn
    1.72
    Tip
    1.71
    Sometimes
    1.71
    Use
    1.70
    Understanding
    1.66
    Remember
    1.66
    Know
    1.65
    Activations Density 0.347%

    No Known Activations