© 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. 1-RES-JB
    11. 22215
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Egypt"

    oai_token-act-pair · gpt-3.5-turbo

    references to Egypt and its people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasses
    -0.83
    âĺħâĺħ
    -0.78
     Kessler
    -0.77
    amins
    -0.72
    ////////////////////////////////
    -0.71
     Scotch
    -0.70
     Nationwide
    -0.69
    hips
    -0.68
    present
    -0.68
    CLOSE
    -0.68
    POSITIVE LOGITS
     Egypt
    1.03
     Egyptians
    0.98
     Pharaoh
    0.91
     Egyptian
    0.85
    araoh
    0.82
     Mubarak
    0.81
     eleph
    0.80
    Egypt
    0.80
     Khe
    0.78
     Sinai
    0.78
    Activations Density 0.009%

    No Known Activations