© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 9953
    Prev
    Next
    INDEX
    Explanations

    mentions of political events related to annexation

    oai_token-act-pair · gpt-3.5-turbo

    references to military annexations and occupations

    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
    Monitor
    -0.87
    answered
    -0.77
    DragonMagazine
    -0.75
    drawn
    -0.71
     preval
    -0.70
    tip
    -0.70
    rences
    -0.69
    eff
    -0.68
     referrals
    -0.68
    LESS
    -0.67
    POSITIVE LOGITS
     Crimea
    1.28
     Yugoslavia
    1.13
     Normandy
    1.04
     Cambodia
    1.03
     Poland
    1.02
     Libya
    0.98
     Iraq
    0.96
     Sicily
    0.95
     Ukraine
    0.93
     Serbia
    0.93
    Activations Density 0.153%

    No Known Activations