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. 10-RES-JB
    6. 17814
    Prev
    Next
    INDEX
    Explanations

    instances of the word "por" and other variations in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, particularly related to the name Poroshenko

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ames
    -0.69
     sorts
    -0.66
    enegger
    -0.66
     Radiation
    -0.64
    ITED
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
    âĦ¢:
    -0.62
    INESS
    -0.61
     Hav
    -0.61
    ITNESS
    -0.61
    POSITIVE LOGITS
    oshenko
    1.31
    cup
    1.29
    cel
    1.19
    ters
    1.10
    folios
    1.06
    cus
    1.05
    bably
    1.05
    ridge
    1.00
    por
    0.98
    cer
    0.98
    Activations Density 0.024%

    No Known Activations