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. 1-RES-JB
    6. 23937
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Niklas"

    oai_token-act-pair · gpt-3.5-turbo

    references to the 'Atlas' and 'Niklas', possibly in the context of sports or competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fecture
    -0.80
    ãģĭ
    -0.73
    merce
    -0.73
    ebook
    -0.72
    tails
    -0.71
    DIT
    -0.69
    RANT
    -0.68
    intent
    -0.65
    Discussion
    -0.65
    PUT
    -0.64
    POSITIVE LOGITS
    las
    1.22
    quez
    0.91
    chwitz
    0.81
    hee
    0.80
    gow
    0.80
    aurus
    0.79
    cano
    0.79
    ques
    0.78
    zsche
    0.77
    alus
    0.77
    Activations Density 0.004%

    No Known Activations