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. 5710
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions or anatomical structures ending in 'ural'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of "ural" or "structural" concepts, indicating an emphasis on structures and systems in different contexts

    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
    â̳
    -0.74
    DN
    -0.64
     Decker
    -0.63
     LINE
    -0.62
     RIP
    -0.61
     Ames
    -0.59
     Sawyer
    -0.59
    etts
    -0.59
     Spartan
    -0.58
     Knife
    -0.58
    POSITIVE LOGITS
    ural
    1.31
    idad
    0.83
    ategory
    0.81
    interstitial
    0.76
    urally
    0.76
    tarian
    0.74
    ãĥ¥
    0.74
    ertain
    0.72
    ultural
    0.72
    ised
    0.72
    Activations Density 0.003%

    No Known Activations