© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22899
    Prev
    Next
    INDEX
    Explanations

    terms related to the country Venezuela

    oai_token-act-pair · gpt-3.5-turbo

    mentions and references to Venezuela

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alty
    -0.98
    frames
    -0.90
    ificantly
    -0.88
    ãģĨ
    -0.86
    frame
    -0.86
    sbm
    -0.83
    onym
    -0.79
    å§«
    -0.78
    shaw
    -0.78
    erman
    -0.77
    POSITIVE LOGITS
     Maduro
    1.13
     Chavez
    0.98
     Venezuela
    0.93
    enezuel
    0.91
     Venezuel
    0.88
     Venezuelan
    0.82
     dictator
    0.78
     Bolivia
    0.75
     Tripoli
    0.71
    illo
    0.71
    Activations Density 0.009%

    No Known Activations