© 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. 3026
    Prev
    Next
    INDEX
    Explanations

    references to different nationalities and countries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of nationalities and their corresponding sports contexts

    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
    ÅĤ
    -0.86
    aucus
    -0.86
     Navajo
    -0.78
     )]
    -0.76
    20439
    -0.76
     Pastebin
    -0.73
    isSpecialOrderable
    -0.73
    olitics
    -0.72
    idem
    -0.71
    ufact
    -0.70
    POSITIVE LOGITS
     midfielder
    1.14
     Championship
    1.14
     league
    1.14
     goalkeeper
    1.12
     striker
    1.09
     Athletic
    1.09
     winger
    1.08
     footballer
    1.08
     superstar
    1.06
     Football
    1.04
    Activations Density 0.077%

    No Known Activations