© 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. 1-RES-JB
    11. 3551
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ceasefire."

    oai_token-act-pair · gpt-3.5-turbo

    references to ceasefires and truces in conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lear
    -0.90
    Av
    -0.82
    Leary
    -0.79
    Americans
    -0.76
    Heat
    -0.75
    Hop
    -0.73
    Individual
    -0.73
    Kin
    -0.73
    AMES
    -0.73
    Cloud
    -0.71
    POSITIVE LOGITS
     ceasefire
    1.53
     truce
    1.41
     hostilities
    0.89
     conflic
    0.86
     cease
    0.86
     rul
    0.83
     cessation
    0.83
     agre
    0.83
    ascus
    0.79
     disarm
    0.79
    Activations Density 0.006%

    No Known Activations