© 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 EvalsExportsAPI 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. 3836
    Prev
    Next
    INDEX
    Explanations

    references to the United Nations Security Council

    oai_token-act-pair · gpt-3.5-turbo

    references to the UN Security Council and its activities

    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
    icio
    -0.74
    Downloadha
    -0.74
    udeau
    -0.73
     experien
    -0.70
    CTV
    -0.69
    TPS
    -0.66
     goose
    -0.64
     gardening
    -0.64
    href
    -0.62
     farmer
    -0.62
    POSITIVE LOGITS
     Directive
    1.00
    member
    0.93
    members
    0.88
    s
    0.83
    Member
    0.81
     Members
    0.77
     Council
    0.76
     Headquarters
    0.74
    pers
    0.73
     Chambers
    0.73
    Activations Density 0.044%

    No Known Activations