© 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. 1-RES-JB
    11. 3663
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Venezuela"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Venezuela and its related political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    frames
    -0.84
    姫
    -0.81
    onym
    -0.80
    alty
    -0.78
    yll
    -0.77
    frame
    -0.77
    ãģĨ
    -0.77
    sbm
    -0.76
    erman
    -0.75
    ificantly
    -0.75
    POSITIVE LOGITS
     Maduro
    1.32
     Venezuela
    1.12
    enezuel
    1.10
     Chavez
    1.05
     Venezuel
    0.96
     Venezuelan
    0.95
    acas
    0.87
     Bolivia
    0.79
     Tripoli
    0.76
    ktop
    0.75
    Activations Density 0.009%

    No Known Activations