© 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. 9-RES-JB
    11. 14777
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic efforts and agreements

    oai_token-act-pair · gpt-3.5-turbo

    instances of discussions related to peace negotiations and diplomatic agreements

    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
    mson
    -1.06
     Advertising
    -0.78
    roo
    -0.77
     anecd
    -0.76
    tick
    -0.75
    Skip
    -0.72
     Painter
    -0.72
    Fle
    -0.70
    æ©Ł
    -0.69
    fortune
    -0.69
    POSITIVE LOGITS
     reconciliation
    1.47
     ceasefire
    1.34
     reun
    1.26
     peace
    1.24
     unification
    1.22
     negotiations
    1.21
     truce
    1.19
     disarm
    1.19
     peaceful
    1.17
     treaties
    1.15
    Activations Density 0.623%

    No Known Activations