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. 750
    Prev
    Next
    INDEX
    Explanations

    descriptions of various involvements, such as accidents, unlawful activities, efforts, participation in events or projects, conflicts, maintenance, and conspiracies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to accidents, legal issues, and unlawful activities

    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
    icons
    -0.75
    AppData
    -0.68
    ographers
    -0.68
    inters
    -0.66
    ishes
    -0.65
     flakes
    -0.64
    acers
    -0.63
    âĢ¢âĢ¢
    -0.63
    plets
    -0.63
    zers
    -0.62
    POSITIVE LOGITS
     behalf
    0.85
     affairs
    0.81
     manner
    0.81
     upkeep
    0.80
     arrang
    0.79
     reconstruction
    0.77
     fundraising
    0.77
     promotion
    0.71
     taxation
    0.71
     rendition
    0.69
    Activations Density 0.573%

    No Known Activations