© 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. 10-RES-JB
    11. 13584
    Prev
    Next
    INDEX
    Explanations

    mentions of the international community and requests for their involvement or action

    oai_token-act-pair · gpt-3.5-turbo

    references to the international community and its involvement in global issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenberg
    -0.85
    alach
    -0.78
    ippi
    -0.78
    issa
    -0.75
    ertation
    -0.74
     Canter
    -0.72
    atoon
    -0.71
     Clerk
    -0.69
     Gleaming
    -0.68
     Fres
    -0.66
    POSITIVE LOGITS
     diplomats
    1.10
     observers
    1.08
     sanctions
    1.07
     nations
    1.03
     envoy
    0.99
     diplomatic
    0.98
     diplomat
    0.98
     countries
    0.97
     monitors
    0.97
     humanitarian
    0.96
    Activations Density 0.138%

    No Known Activations