© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20308
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Egypt

    oai_token-act-pair · gpt-3.5-turbo

    references to Egypt

    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
    ////////////////////////////////
    -0.79
     Reilly
    -0.72
    ctl
    -0.70
     blu
    -0.68
    NN
    -0.68
    STD
    -0.67
    Blu
    -0.65
     tagged
    -0.63
    andom
    -0.63
     wra
    -0.62
    POSITIVE LOGITS
     Egypt
    3.73
    Egypt
    3.25
     Egyptians
    2.67
     Egyptian
    2.67
     Cairo
    2.47
     Sinai
    2.00
     Pharaoh
    1.96
     Ethiopia
    1.93
    gypt
    1.92
     Tunisia
    1.92
    Activations Density 0.009%

    No Known Activations