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. 15590
    Prev
    Next
    INDEX
    Explanations

    hyperlinks

    oai_token-act-pair · gpt-3.5-turbo

    URLs and links to websites or online content

    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
     unsus
    -0.74
     Palest
    -0.72
     destro
    -0.72
     unfinished
    -0.69
    joined
    -0.67
     Bots
    -0.64
     unaffected
    -0.64
    itiz
    -0.61
     Osc
    -0.61
    pora
    -0.61
    POSITIVE LOGITS
    ://
    1.20
    www
    1.08
     www
    0.88
    erences
    0.83
    doi
    0.77
    youtu
    0.74
    web
    0.73
    img
    0.73
     youtube
    0.72
    twitter
    0.72
    Activations Density 0.024%

    No Known Activations