© 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. 18294
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or international tensions

    oai_token-act-pair · gpt-3.5-turbo

    references to rising tensions or conflicts between entities

    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
    cise
    -0.75
    prints
    -0.74
     Upload
    -0.73
    Chance
    -0.66
    ITNESS
    -0.65
     recipient
    -0.64
     recipients
    -0.62
    issance
    -0.62
     omission
    -0.62
    sites
    -0.61
    POSITIVE LOGITS
     tensions
    1.06
     flared
    1.04
     simmer
    0.98
     escal
    0.97
     tension
    0.94
     flare
    0.89
     cooker
    0.86
     escalate
    0.85
     between
    0.81
     unresolved
    0.81
    Activations Density 0.094%

    No Known Activations