© 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. 1-RES-JB
    11. 16406
    Prev
    Next
    INDEX
    Explanations

    medical specialties related to women's health

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical and clinical fields, particularly obstetrics and pediatrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leaf
    -0.63
    ifest
    -0.63
    EMBER
    -0.62
     Proposition
    -0.62
     fetus
    -0.62
     descend
    -0.60
     ancestor
    -0.59
     spirit
    -0.59
    Construct
    -0.59
     unpaid
    -0.59
    POSITIVE LOGITS
    rics
    1.46
    hower
    1.02
    awei
    0.95
    iology
    0.92
    hooting
    0.88
    peed
    0.85
    kaya
    0.82
    rences
    0.81
     guiActiveUn
    0.81
    mith
    0.81
    Activations Density 0.022%

    No Known Activations