© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 22482
    Prev
    Next
    INDEX
    Explanations

    mentions of specific countries, with a focus on Egypt

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Egypt and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĺħâĺħ
    -0.82
     Kessler
    -0.76
    hips
    -0.75
    amins
    -0.74
     Louisville
    -0.71
    think
    -0.71
     Bowman
    -0.68
    lasses
    -0.66
     Connor
    -0.65
     Pittsburgh
    -0.65
    POSITIVE LOGITS
    osph
    0.87
     Egyptians
    0.87
     hier
    0.83
    ologists
    0.82
    Air
    0.81
    ological
    0.79
    inx
    0.77
     Pharaoh
    0.77
     Egypt
    0.76
    ologic
    0.75
    Activations Density 0.034%

    No Known Activations