© 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. 4-RES-JB
    11. 14585
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terms, including diseases, medical procedures, and health conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related topics, particularly involving diseases and treatments

    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
    ioxide
    -0.61
    ä½ľ
    -0.60
    akeru
    -0.59
     constitu
    -0.57
    enum
    -0.56
    anasia
    -0.56
    å¦
    -0.54
    ç«
    -0.53
    anse
    -0.53
    ettel
    -0.52
    POSITIVE LOGITS
    ico
    0.59
     buffalo
    0.52
    rero
    0.49
     or
    0.48
    /
    0.48
     flask
    0.48
     Flask
    0.46
     shark
    0.46
    ModLoader
    0.44
     hook
    0.44
    Activations Density 1.955%

    No Known Activations