© 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. 1-RES-JB
    11. 16908
    Prev
    Next
    INDEX
    Explanations

    references or mentions of the United Nations (UN) in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the United Nations (UN)

    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
    thora
    -0.82
     Camb
    -0.73
    Ö¼
    -0.73
    hetti
    -0.72
    士
    -0.70
    stals
    -0.68
     Mechdragon
    -0.67
     Elect
    -0.66
    ãĤ¼
    -0.66
     Demons
    -0.66
    POSITIVE LOGITS
    SC
    0.97
    KNOWN
    0.95
     UN
    0.95
    ilateral
    0.85
    ICE
    0.84
    DEC
    0.82
    UN
    0.82
    IF
    0.81
    namese
    0.80
     envoy
    0.80
    Activations Density 0.007%

    No Known Activations