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. 12-RES-JB
    6. 15099
    Prev
    Next
    INDEX
    Explanations

    mentions of trailers for upcoming games in a specific series

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to specific video game series and their characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pitt
    -1.00
     Lyons
    -0.87
    Moscow
    -0.87
     Charlottesville
    -0.84
     Steelers
    -0.82
     steril
    -0.80
    Soviet
    -0.80
     Vegas
    -0.80
    tein
    -0.79
    ottesville
    -0.79
    POSITIVE LOGITS
     Link
    1.64
     Zelda
    1.52
     Piece
    1.22
     Legend
    1.19
     Breath
    1.17
    Link
    1.17
     Luffy
    1.16
     Gan
    1.14
     Korra
    1.13
     Avatar
    1.12
    Activations Density 0.121%

    No Known Activations