Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14447
    Prev
    Next
    INDEX
    Explanations

    words related to production or manufacturing processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to production and introduction of various concepts or items

    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
     Frankfurt
    -0.71
    oday
    -0.67
    oola
    -0.64
    AIN
    -0.63
     Io
    -0.62
    ORE
    -0.62
    uyomi
    -0.60
    è¦ļéĨĴ
    -0.60
    é¾įå¥ij士
    -0.58
     Everywhere
    -0.58
    POSITIVE LOGITS
    cing
    2.07
    ced
    1.88
    ctions
    1.85
    cer
    1.78
    ctory
    1.64
    cers
    1.61
    ces
    1.61
    ctive
    1.57
    ce
    1.57
    ction
    1.55
    Activations Density 0.084%

    No Known Activations