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. 0-RES-JB
    6. 17549
    Prev
    Next
    INDEX
    Explanations

    references to healthcare-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to health care topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reloaded
    -0.83
    kat
    -0.72
    UA
    -0.68
    mini
    -0.68
    gren
    -0.65
     Rubin
    -0.63
     Slam
    -0.63
    itri
    -0.62
    Draft
    -0.62
    kan
    -0.62
    POSITIVE LOGITS
     care
    3.71
     Care
    2.60
    care
    2.36
     cared
    2.25
     CARE
    2.12
     cares
    1.99
     caring
    1.99
    Care
    1.85
     caregivers
    1.35
     careg
    1.32
    Activations Density 0.022%

    No Known Activations