© 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. 4-RES-JB
    11. 16641
    Prev
    Next
    INDEX
    Explanations

    verbs related to military action and capturing territory or locations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military operations and territory control

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

    No Comments

    Negative Logits
    ¢
    -0.84
    thur
    -0.81
     Lifetime
    -0.78
    Sport
    -0.74
    Scot
    -0.73
     Mercury
    -0.73
     actu
    -0.73
    Consumer
    -0.73
    Phys
    -0.71
    spir
    -0.71
    POSITIVE LOGITS
     Donetsk
    1.15
     Aleppo
    1.14
     Tripoli
    1.12
     Libya
    1.10
     Idlib
    1.10
     Raqqa
    1.09
     Libyan
    1.06
     Mosul
    1.04
     Yemeni
    1.04
     Syria
    1.02
    Activations Density 0.273%

    No Known Activations