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. 21660
    Prev
    Next
    INDEX
    Explanations

    names containing the letters "oy"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Foy" in various contexts

    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
    İĭ
    -0.76
     Zeit
    -0.74
    idency
    -0.68
     ende
    -0.62
     obligated
    -0.61
     digitally
    -0.61
     totality
    -0.60
    uyomi
    -0.59
     tampering
    -0.58
     conflic
    -0.58
    POSITIVE LOGITS
    oy
    0.97
    oga
    0.92
    nih
    0.91
    bean
    0.89
    ster
    0.86
    outube
    0.85
    enne
    0.83
    uan
    0.83
    nton
    0.82
    aml
    0.82
    Activations Density 0.013%

    No Known Activations