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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12142
    Prev
    Next
    INDEX
    Explanations

    words associated with cleaning and medical treatments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drugs and their effects, particularly concerning health and medical usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hedral
    -0.82
    eday
    -0.76
    aucuses
    -0.74
    onde
    -0.73
    join
    -0.71
    erial
    -0.70
    archive
    -0.69
    union
    -0.69
    merce
    -0.69
    halla
    -0.69
    POSITIVE LOGITS
     agents
    1.26
     agent
    1.21
     measures
    1.18
     mechanisms
    1.15
     medication
    1.14
     drugs
    1.12
     properties
    1.12
     medications
    1.10
     Measures
    1.08
     effects
    1.08
    Activations Density 0.224%

    No Known Activations