© 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. 10-RES-JB
    11. 18796
    Prev
    Next
    INDEX
    Explanations

    mentions of geopolitical locations and political situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geopolitical capital and territorial status in the context of Israel and Palestine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     motivational
    -0.80
     stunts
    -0.79
     skew
    -0.79
     thrill
    -0.77
     upbeat
    -0.77
    maxwell
    -0.73
    nox
    -0.73
     brainstorm
    -0.72
     salon
    -0.72
     reviewers
    -0.72
    POSITIVE LOGITS
     sovereignty
    1.62
     territ
    1.50
     annexed
    1.40
     annexation
    1.39
     secession
    1.38
     territories
    1.35
     territorial
    1.33
     sovereign
    1.32
     borders
    1.32
     Territ
    1.28
    Activations Density 0.640%

    No Known Activations