© 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. 4-RES-JB
    11. 735
    Prev
    Next
    INDEX
    Explanations

    names of countries, especially Peru

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Peru and related geographical or health topics

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

    No Comments

    Negative Logits
    enegger
    -0.99
    hire
    -0.84
    hips
    -0.81
    haw
    -0.80
    hog
    -0.79
    ////////////////////////////////
    -0.79
    roads
    -0.76
    ////////////////
    -0.76
    ues
    -0.76
    breakers
    -0.75
    POSITIVE LOGITS
     Peru
    0.82
    bably
    0.78
    uvian
    0.77
     hiking
    0.70
     Pradesh
    0.68
     expedition
    0.68
     Peoples
    0.67
     compr
    0.66
     Rica
    0.65
     gardening
    0.65
    Activations Density 0.021%

    No Known Activations