© 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. 9-RES-JB
    11. 4098
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, regulations, and international agreements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to arms regulations and illicit trade

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     brim
    -0.99
     hog
    -0.95
    natureconservancy
    -0.90
     doom
    -0.81
     cider
    -0.80
     yak
    -0.80
     racer
    -0.79
     brew
    -0.79
     queen
    -0.78
     melt
    -0.78
    POSITIVE LOGITS
     Devices
    1.32
     Reporting
    1.28
     Activities
    1.26
     Associ
    1.25
     Practices
    1.23
     Surveillance
    1.20
     Prevention
    1.19
     Procedures
    1.16
     Implementation
    1.16
     Diseases
    1.16
    Activations Density 0.287%

    No Known Activations