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. 16705
    Prev
    Next
    INDEX
    Explanations

    words related to military conflicts or battles

    oai_token-act-pair · gpt-3.5-turbo

    references to combat, wars, or conflicts

    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
    ADRA
    -0.85
    ewitness
    -0.75
    Sample
    -0.72
    Chance
    -0.69
    Live
    -0.67
    vae
    -0.65
    mson
    -0.64
    utch
    -0.63
    oba
    -0.63
    Fac
    -0.62
    POSITIVE LOGITS
    iest
    0.95
     fray
    0.88
    osphere
    0.86
     trenches
    0.79
     waged
    0.72
     unfolding
    0.72
     trench
    0.71
     arena
    0.71
     raging
    0.71
    naires
    0.69
    Activations Density 0.189%

    No Known Activations