© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 17328
    Prev
    Next
    INDEX
    Explanations

    information related to various types of health care, including medical treatments, health policies, and physical conditions

    oai_token-act-pair · gpt-3.5-turbo

    tokens that indicate the start or end of a text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vaugh
    -0.71
    retty
    -0.60
    pload
    -0.58
    lyak
    -0.57
    avorite
    -0.57
    ãĥ¼ãĥ³
    -0.57
    lol
    -0.57
    anu
    -0.56
    代
    -0.56
     Niet
    -0.56
    POSITIVE LOGITS
     NHS
    0.61
    ependent
    0.60
     regulated
    0.58
    esity
    0.58
     nursing
    0.55
     nutrients
    0.54
     insured
    0.54
     âĢº
    0.54
    ersive
    0.54
    dependent
    0.53
    Activations Density 1.031%

    No Known Activations