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. 3-RES-JB
    6. 19888
    Prev
    Next
    INDEX
    Explanations

    best-selling or highly popular items, such as books, music albums, and games

    oai_token-act-pair · gpt-3.5-turbo

    references to best-selling items and their success in sales rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterdam
    -0.78
    zik
    -0.77
     Lod
    -0.70
     Kear
    -0.65
     lag
    -0.65
     Mesh
    -0.62
    irm
    -0.62
     Deck
    -0.62
     sshd
    -0.62
     customs
    -0.61
    POSITIVE LOGITS
    selling
    0.97
    Interstitial
    0.91
    seller
    0.91
    sell
    0.89
    ONSORED
    0.89
    atform
    0.89
    stores
    0.88
    代
    0.85
    ãĥł
    0.84
    BuyableInstoreAndOnline
    0.84
    Activations Density 0.023%

    No Known Activations