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. 4-RES-JB
    6. 8689
    Prev
    Next
    INDEX
    Explanations

    medical conditions and related symptoms

    oai_token-act-pair · gpt-3.5-turbo

    medical conditions and advice related to health

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

    No Comments

    Negative Logits
    Untitled
    -0.90
    ysc
    -0.81
    ãĥķãĤ©
    -0.75
    twitter
    -0.74
     retweet
    -0.73
    Render
    -0.72
    Translation
    -0.71
    Marx
    -0.71
    icons
    -0.69
     widget
    -0.69
    POSITIVE LOGITS
     Symptoms
    1.21
     medication
    1.12
     medications
    1.12
     symptoms
    1.10
     careg
    1.08
     caregivers
    1.07
     nutritional
    1.02
     lact
    1.02
     pediatric
    1.02
     vascular
    1.02
    Activations Density 1.064%

    No Known Activations