© 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. 9-RES-JB
    11. 4299
    Prev
    Next
    INDEX
    Explanations

    phrases related to drugs and medical substances

    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
    borgh
    -0.64
     Dialogue
    -0.63
    DragonMagazine
    -0.61
    Ô
    -0.60
    ¢
    -0.60
     Westminster
    -0.60
     Consent
    -0.59
    ventus
    -0.59
     Assignment
    -0.57
    bernatorial
    -0.57
    POSITIVE LOGITS
     itself
    0.97
    's
    0.82
     formerly
    0.75
    iverse
    0.71
    ieth
    0.69
    wright
    0.68
    osphere
    0.68
    atics
    0.68
     extensively
    0.67
    formerly
    0.64
    Activations Density 0.476%

    No Known Activations