© 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. 10648
    Prev
    Next
    INDEX
    Explanations

    location names embedded in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to political and military events in Afghanistan

    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
     Saturn
    -0.86
     Daytona
    -0.86
     Mercer
    -0.83
     ESA
    -0.83
    Disney
    -0.82
    byss
    -0.82
    Elsa
    -0.82
     Pelicans
    -0.80
     Charlotte
    -0.79
     Asheville
    -0.79
    POSITIVE LOGITS
     Pakistan
    2.25
     Pakistani
    2.21
    Pakistan
    2.17
     Islamabad
    2.17
     Karachi
    1.96
     Taliban
    1.95
     Kabul
    1.91
     Afghan
    1.90
    Pak
    1.84
     Kashmir
    1.72
    Activations Density 0.294%

    No Known Activations