© 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. 3-RES-JB
    11. 14749
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations and ethnic groups, specifically focusing on areas like Eurasia and mentioning various ethnicities such as Mongolian and Caucasian

    oai_token-act-pair · gpt-3.5-turbo

    references to various ethnic and regional identities, particularly those associated with Eurasia and Mongolia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    houses
    -0.77
    VL
    -0.72
    enegger
    -0.72
    ISA
    -0.72
    house
    -0.72
    zl
    -0.68
    BALL
    -0.68
    ded
    -0.67
    nl
    -0.67
    ulton
    -0.67
    POSITIVE LOGITS
     Euras
    0.83
    aucas
    0.78
    oid
    0.75
    oids
    0.74
     territ
    0.74
    inia
    0.73
     Empires
    0.72
     Expedition
    0.72
    istani
    0.71
     perspect
    0.71
    Activations Density 0.010%

    No Known Activations