© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2842
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic negotiations and peace agreements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to diplomatic negotiations and peace agreements

    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
    mson
    -0.90
     Gund
    -0.75
     Huck
    -0.72
     Advertising
    -0.72
    tick
    -0.70
     Painter
    -0.69
     unlucky
    -0.69
     Draper
    -0.69
     Moff
    -0.68
    advertisement
    -0.68
    POSITIVE LOGITS
     reconciliation
    1.45
     peace
    1.43
     ceasefire
    1.33
     peaceful
    1.31
     disarm
    1.26
     reun
    1.25
     dialogue
    1.23
     truce
    1.23
     peacefully
    1.22
     negotiations
    1.12
    Activations Density 0.412%

    No Known Activations