© 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. 3-RES-JB
    11. 543
    Prev
    Next
    INDEX
    Explanations

    words related to bravery or courageous actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "brave" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.76
    yrinth
    -0.73
    hops
    -0.71
    urgy
    -0.70
    vp
    -0.69
    entity
    -0.67
    DERR
    -0.66
     disqualified
    -0.66
    agree
    -0.63
    iphate
    -0.63
    POSITIVE LOGITS
    ly
    0.93
     enough
    0.82
     brave
    0.77
     courage
    0.76
    ï¸
    0.73
    zes
    0.73
     souls
    0.73
    glers
    0.72
    heart
    0.72
    faced
    0.71
    Activations Density 0.010%

    No Known Activations