© 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. 10-RES-JB
    11. 16970
    Prev
    Next
    INDEX
    Explanations

    political and economic terms related to Venezuela

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and events in Venezuela

    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
     Halo
    -1.04
     Celtics
    -1.03
     Bungie
    -1.02
     Berkshire
    -0.93
     Celtic
    -0.92
     Norse
    -0.92
    orkshire
    -0.89
     Bradford
    -0.88
     Viking
    -0.87
    Boston
    -0.86
    POSITIVE LOGITS
     Maduro
    2.18
     Venezuel
    2.01
     Venezuelan
    1.94
     Venezuela
    1.86
     Chavez
    1.81
    enezuel
    1.69
     democratically
    1.39
     dictatorship
    1.33
     socialist
    1.32
    acas
    1.26
    Activations Density 0.421%

    No Known Activations