© 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. 2-RES-JB
    11. 17187
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ceasefire" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to ceasefires and truces in conflict situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lear
    -0.85
    AMES
    -0.82
    Leary
    -0.82
    Americans
    -0.80
    Av
    -0.74
    aunder
    -0.73
    aum
    -0.71
     Bath
    -0.70
    yon
    -0.70
    Merit
    -0.70
    POSITIVE LOGITS
     ceasefire
    1.39
     truce
    1.23
     hostilities
    0.87
     conflic
    0.84
     treaty
    0.84
     agreement
    0.83
     peace
    0.81
     blockade
    0.81
     cease
    0.81
     standoff
    0.81
    Activations Density 0.007%

    No Known Activations