© 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. 0-RES-JB
    11. 21779
    Prev
    Next
    INDEX
    Explanations

    mentions of ceasefire agreements or violations

    oai_token-act-pair · gpt-3.5-turbo

    references to ceasefires and truces in conflict discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Swanson
    -0.71
    roman
    -0.70
     DeV
    -0.68
    essors
    -0.66
    Ed
    -0.66
     Sims
    -0.66
    tu
    -0.65
    agen
    -0.64
    wr
    -0.64
     Edison
    -0.64
    POSITIVE LOGITS
     ceasefire
    3.66
     truce
    2.64
     cessation
    1.27
     curfew
    1.24
     peace
    1.14
     cease
    1.13
     blockade
    1.12
     Nato
    1.10
     reconc
    1.10
     disarm
    1.08
    Activations Density 0.023%

    No Known Activations