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. 2-RES-JB
    6. 19272
    Prev
    Next
    INDEX
    Explanations

    mentions of names or terms related to the Olympic Games

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Moly" and variations of the term "amorph."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ño
    -0.75
    izen
    -0.70
    IDENT
    -0.67
    CAP
    -0.66
     Citation
    -0.65
     Quit
    -0.64
    BIP
    -0.63
     Parables
    -0.62
     Twain
    -0.62
    inelli
    -0.61
    POSITIVE LOGITS
    oly
    1.38
    sis
    1.00
    gon
    0.97
    rics
    0.95
    tes
    0.91
    tics
    0.88
    mers
    0.87
    tic
    0.87
    cus
    0.85
    anes
    0.85
    Activations Density 0.010%

    No Known Activations