© 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. 2-RES-JB
    11. 8923
    Prev
    Next
    INDEX
    Explanations

    phrases related to the military

    oai_token-act-pair · gpt-3.5-turbo

    references to the military

    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
    20439
    -0.96
    DAY
    -0.82
    âĶģ
    -0.80
    heimer
    -0.79
    terness
    -0.75
     GOODMAN
    -0.75
     Blessed
    -0.74
    Honest
    -0.74
    atron
    -0.73
    apest
    -0.72
    POSITIVE LOGITS
     acad
    1.02
     academy
    1.01
     fatig
    0.99
     personnel
    0.97
     contractor
    0.91
     occupation
    0.89
     dictatorship
    0.89
     intervention
    0.88
     jargon
    0.87
     commanders
    0.86
    Activations Density 0.028%

    No Known Activations