© 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. 9906
    Prev
    Next
    INDEX
    Explanations

    words related to specific countries involved in conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to the Iraq and Syria 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
    atin
    -0.89
    thereum
    -0.74
    iple
    -0.73
    bery
    -0.71
     newcom
    -0.68
    onym
    -0.68
    haw
    -0.67
     Wim
    -0.64
    rotein
    -0.64
    ateur
    -0.64
    POSITIVE LOGITS
     ravaged
    0.79
     Reconstruction
    0.73
     Syndrome
    0.73
     milit
    0.71
     invaded
    0.70
     annex
    0.69
    istan
    0.68
     flared
    0.66
     looms
    0.66
     devastated
    0.66
    Activations Density 0.122%

    No Known Activations