© 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. 10-RES-JB
    11. 16600
    Prev
    Next
    INDEX
    Explanations

    names of countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of nationalities and countries

    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
    lov
    -0.87
    eus
    -0.86
    vg
    -0.82
    thia
    -0.77
    possibly
    -0.77
    redd
    -0.77
    limited
    -0.76
    yers
    -0.75
    arettes
    -0.75
    illary
    -0.74
    POSITIVE LOGITS
     embassy
    1.24
     consulate
    1.21
     Embassy
    1.19
     government
    1.15
     Federation
    1.10
     economy
    1.06
     ambassador
    1.06
     populace
    1.04
     presidency
    1.02
     equivalent
    1.02
    Activations Density 0.120%

    No Known Activations