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. 21584
    Prev
    Next
    INDEX
    Explanations

    social media platforms and links to websites in the form of URLs

    oai_token-act-pair · gpt-3.5-turbo

    references to social media and newsletter subscriptions

    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
    eus
    -0.81
    gow
    -0.78
     ¶
    -0.66
    icago
    -0.64
    vironments
    -0.62
    eton
    -0.62
    imer
    -0.61
    £ı
    -0.58
    usha
    -0.57
    owship
    -0.56
    POSITIVE LOGITS
    CHAT
    0.63
    thumbnails
    0.61
    200000
    0.53
    hani
    0.52
    _-
    0.51
    ANI
    0.51
    Post
    0.51
    lish
    0.50
    Vote
    0.49
    stantial
    0.49
    Activations Density 0.123%

    No Known Activations