© 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. 11-RES-JB
    11. 11796
    Prev
    Next
    INDEX
    Explanations

    phrases related to war and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to long-term conflicts and wars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Magikarp
    -0.91
    ULTS
    -0.76
     Edison
    -0.74
     LLP
    -0.71
     Gins
    -0.71
     Cohn
    -0.69
     Modest
    -0.66
     FedEx
    -0.66
     laure
    -0.66
    ertodd
    -0.65
    POSITIVE LOGITS
     insurgency
    1.43
     conflict
    1.39
     uprising
    1.29
     ceasefire
    1.24
     bloodshed
    1.23
     siege
    1.21
     war
    1.21
     sectarian
    1.19
     hostilities
    1.18
     civil
    1.16
    Activations Density 0.245%

    No Known Activations