© 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 EvalsExportsinterp-engineNEWAPI 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. 4180
    Prev
    Next
    INDEX
    Explanations

    phrases related to military airstrikes and bombings

    oai_token-act-pair · gpt-3.5-turbo

    references to military actions and airstrikes

    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
     heirs
    -0.72
     Gems
    -0.71
     founders
    -0.71
     Guru
    -0.70
     Eggs
    -0.70
     Invention
    -0.70
    ospels
    -0.70
     Alchemy
    -0.70
     trivia
    -0.69
     afterlife
    -0.69
    POSITIVE LOGITS
     indiscrim
    1.25
     airstrikes
    1.20
     targeting
    1.18
     retali
    1.18
     intensified
    1.08
     airstrike
    1.06
     bombing
    1.05
     aimed
    1.04
    Operation
    1.01
     militar
    1.01
    Activations Density 0.620%

    No Known Activations