© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7867
    Prev
    Next
    INDEX
    Explanations

    words related to bravery or courage

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to bravery and courage

    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
    isite
    -0.89
     Dise
    -0.76
    isites
    -0.72
    odynam
    -0.71
    orgetown
    -0.69
    enfranch
    -0.69
     elig
    -0.67
     Gutenberg
    -0.62
     contrace
    -0.61
     Controlled
    -0.60
    POSITIVE LOGITS
    faced
    1.24
     brave
    1.01
    face
    0.96
    heart
    0.93
     daring
    0.92
     courageous
    0.90
     souls
    0.87
     courage
    0.84
     defiance
    0.84
    Brave
    0.81
    Activations Density 0.127%

    No Known Activations