© 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. 10-RES-JB
    11. 18703
    Prev
    Next
    INDEX
    Explanations

    locations and events related to conflict or attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents and attacks

    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
    Utah
    -0.87
     Lifetime
    -0.82
    Calif
    -0.81
    Native
    -0.81
    Ohio
    -0.77
    USA
    -0.76
    flix
    -0.72
    orea
    -0.72
    Wisconsin
    -0.70
    âĦ¢
    -0.70
    POSITIVE LOGITS
     mosque
    1.32
     palace
    1.16
     Mosque
    1.14
     entrance
    1.10
     entrances
    1.10
     courtyard
    1.09
     barracks
    1.08
     checkpoint
    1.07
     compound
    1.06
     mosques
    1.06
    Activations Density 0.311%

    No Known Activations