© 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 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. 0-RES-JB
    11. 9583
    Prev
    Next
    INDEX
    Explanations

    references to the European Union (EU)

    oai_token-act-pair · gpt-3.5-turbo

    references to the European Union (EU)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Narr
    -0.72
     Pats
    -0.72
     Fort
    -0.69
     Springs
    -0.69
     Marsh
    -0.69
     Clay
    -0.69
     marsh
    -0.68
     Param
    -0.68
     trivia
    -0.68
     Alfred
    -0.68
    POSITIVE LOGITS
    EU
    4.14
    eu
    1.90
    Europe
    1.81
    European
    1.70
    Brexit
    1.65
    Euro
    1.60
    euro
    1.57
     EU
    1.57
    UK
    1.57
    TPP
    1.48
    Activations Density 0.018%

    No Known Activations