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. 9-RES-JB
    6. 21828
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical advice and diagnosis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    specific medical recommendations and actions related to health assessment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.73
    ylum
    -0.70
    ignty
    -0.68
    alone
    -0.68
    mini
    -0.67
    Õ
    -0.65
    aug
    -0.65
    edience
    -0.65
     Rohingya
    -0.65
     friendships
    -0.64
    POSITIVE LOGITS
     administrators
    1.26
     designers
    1.25
     authorities
    1.24
     curator
    1.20
     veterinarian
    1.20
     marketers
    1.18
     admins
    1.17
     editors
    1.17
     organisers
    1.16
     planners
    1.15
    Activations Density 1.438%

    No Known Activations