© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 871
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and treatments, specifically drugs and health issues

    oai_token-act-pair · gpt-3.5-turbo

    single characters that appear in various contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horizont
    -0.76
     Publishers
    -0.64
     Convers
    -0.64
     pecul
    -0.63
     totality
    -0.63
     acron
    -0.63
     compe
    -0.62
     Imper
    -0.62
     Marketing
    -0.62
    WHERE
    -0.61
    POSITIVE LOGITS
    ippers
    1.08
    udd
    1.05
    akings
    1.05
    appy
    1.04
    appings
    1.00
    imb
    1.00
    ugs
    1.00
    utch
    0.98
    arter
    0.98
    iddles
    0.98
    Activations Density 0.120%

    No Known Activations