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. 6-RES-JB
    6. 15918
    Prev
    Next
    INDEX
    Explanations

    phrases related to official statements or announcements

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the symbol "âĢ," which appears to represent some type of formatting or quote mark in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shroud
    -0.74
     zoning
    -0.73
     Mayo
    -0.72
     dust
    -0.71
     plat
    -0.71
     Augusta
    -0.69
     hemor
    -0.68
     Manhattan
    -0.67
     miscarriage
    -0.67
     grips
    -0.67
    POSITIVE LOGITS
    ¹
    1.28
    ª
    1.10
    ł
    1.07
    ¸
    1.00
    ¾
    0.99
    ı
    0.97
    £
    0.96
    »
    0.96
    ²
    0.96
    ³
    0.95
    Activations Density 0.095%

    No Known Activations