Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 21828
    Prev
    Next
    INDEX
    Explanations

    mentions of bravery and courageous behavior

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "brave" and related terms describing courage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arate
    -0.67
    upon
    -0.67
    rogens
    -0.66
    ipal
    -0.65
    apse
    -0.63
    urgy
    -0.62
    DERR
    -0.61
    foreseen
    -0.61
     administrations
    -0.60
    hops
    -0.59
    POSITIVE LOGITS
    ly
    1.14
    heart
    1.12
     souls
    1.01
    glers
    0.86
    faced
    0.83
     hearts
    0.83
    hearted
    0.78
    gest
    0.76
    ï¸ı
    0.76
    Ò
    0.74
    Activations Density 0.063%

    No Known Activations