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

    Neuronpedia

    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. 7-RES-JB
    11. 2004
    Prev
    Next
    INDEX
    Explanations

    references to international diplomacy and political entities, especially the United Nations Security Council

    oai_token-act-pair · gpt-3.5-turbo

    references to the UN Security Council and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veland
    -0.81
     brim
    -0.71
    ahu
    -0.66
     knots
    -0.65
     scissors
    -0.65
     Cyp
    -0.64
     circuitry
    -0.64
     haircut
    -0.63
    oglu
    -0.63
     circuits
    -0.62
    POSITIVE LOGITS
    ailability
    0.91
    akable
    0.74
    nutrition
    0.73
    IFIED
    0.72
    oppable
    0.69
    iliation
    0.66
    owment
    0.66
     intervene
    0.65
    gha
    0.64
    represented
    0.64
    Activations Density 0.126%

    No Known Activations