© 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. 12041
    Prev
    Next
    INDEX
    Explanations

    locations and organizations related to conflict and military operations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to military operations and territorial conflicts

    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
     Wonderland
    -0.59
    ¢
    -0.54
     Hitchcock
    -0.54
     Adjusted
    -0.53
     Lifetime
    -0.53
    Pitt
    -0.53
    itialized
    -0.53
     Roller
    -0.52
     Cary
    -0.52
    inarily
    -0.52
    POSITIVE LOGITS
     Rohingya
    0.84
     Islamist
    0.80
     militant
    0.78
     Shiite
    0.77
     Azerbai
    0.77
     militants
    0.76
     YPG
    0.75
     milit
    0.74
     Daesh
    0.74
     hostages
    0.74
    Activations Density 3.369%

    No Known Activations