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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 7193
    Prev
    Next
    INDEX
    Explanations

    references or mentions related to the United Nations (UN)

    oai_token-act-pair · gpt-3.5-turbo

    references to the United Nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guardiola
    -0.69
     \(
    -0.66
    ynski
    -0.64
     coh
    -0.64
     Klopp
    -0.63
     Achilles
    -0.60
     Malfoy
    -0.59
    ":[{"
    -0.58
     Mania
    -0.58
     subp
    -0.58
    POSITIVE LOGITS
    KNOWN
    1.20
    SC
    1.19
    ICE
    1.16
    IVERS
    1.06
    GA
    1.05
    IX
    1.05
    LV
    1.05
    ITED
    1.03
    ISON
    1.02
    IF
    1.01
    Activations Density 0.024%

    No Known Activations