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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14760
    Prev
    Next
    INDEX
    Explanations

    words related to health and healthcare

    oai_token-act-pair · gpt-3.5-turbo

    references to healthcare-related terminology and policies

    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
    Äĩ
    -0.88
    */(
    -0.88
    ħĭ
    -0.86
    SpaceEngineers
    -0.84
    pole
    -0.83
     Cosponsors
    -0.79
    Publisher
    -0.79
    jac
    -0.77
    hiba
    -0.77
    ãĤ¨ãĥ«
    -0.73
    POSITIVE LOGITS
     wellbeing
    0.76
     wellness
    0.76
     childbirth
    0.73
     safety
    0.70
    tnc
    0.70
     nutrition
    0.69
     Samar
    0.68
     health
    0.67
     healthcare
    0.67
     endangered
    0.67
    Activations Density 0.229%

    No Known Activations