© 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. 11-RES-JB
    11. 14983
    Prev
    Next
    INDEX
    Explanations

    dates and mentions of political actions/events in Venezuela, especially related to oil

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Venezuelan political figures and events

    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
     Bungie
    -1.02
     Celtics
    -1.01
     Halo
    -0.98
     Viking
    -0.97
     Norse
    -0.96
     Celtic
    -0.95
     Vikings
    -0.92
     Dian
    -0.90
     dw
    -0.86
     Runes
    -0.85
    POSITIVE LOGITS
     Maduro
    2.36
     Venezuel
    2.25
     Venezuelan
    2.25
     Venezuela
    2.18
     Chavez
    1.99
    enezuel
    1.91
     Hugo
    1.56
    acas
    1.54
     Bol
    1.53
     Bolivia
    1.37
    Activations Density 0.140%

    No Known Activations