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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2711
    Prev
    Next
    INDEX
    Explanations

    words related to courage

    oai_token-act-pair · gpt-3.5-turbo

    references 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 @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eor
    -0.87
    payer
    -0.75
    washer
    -0.67
    ramid
    -0.65
     Noon
    -0.65
    hemat
    -0.64
    amac
    -0.63
    eren
    -0.63
     Bye
    -0.63
    oval
    -0.61
    POSITIVE LOGITS
    ously
    1.43
     courage
    0.92
    ous
    0.88
    isma
    0.81
    FUL
    0.80
     inspiring
    0.79
    uously
    0.76
     Courage
    0.75
     bravery
    0.75
    uous
    0.74
    Activations Density 0.017%

    No Known Activations