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. 2-RES-JB
    6. 16427
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions or treatments, specifically focusing on 'warts'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences or mentions of "arts."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascus
    -0.71
    phis
    -0.68
    EStream
    -0.68
    è¦ļéĨĴ
    -0.68
    dayName
    -0.67
     cumbers
    -0.65
     occas
    -0.64
    berman
    -0.62
    pora
    -0.62
    PLIED
    -0.62
    POSITIVE LOGITS
    arts
    0.99
    heid
    0.98
    ners
    0.83
    oon
    0.83
    ICLE
    0.82
    heet
    0.80
    oons
    0.80
    ending
    0.77
    esian
    0.76
    emis
    0.76
    Activations Density 0.007%

    No Known Activations