© 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. 7-RES-JB
    11. 19412
    Prev
    Next
    INDEX
    Explanations

    references to specific countries or international relations

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical entities and their relationships or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adobe
    -0.64
    eatures
    -0.63
     acknow
    -0.58
     Pric
    -0.55
    quickShipAvailable
    -0.55
    javascript
    -0.53
    ãĥ´
    -0.52
    ived
    -0.51
     partName
    -0.51
    mble
    -0.51
    POSITIVE LOGITS
     invading
    0.71
     anymore
    0.70
     detriment
    0.70
     invaders
    0.70
     altogether
    0.69
     hegemony
    0.69
    existent
    0.66
     throne
    0.63
    .
    0.63
     confines
    0.62
    Activations Density 0.694%

    No Known Activations