© 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. 8-RES-JB
    11. 17245
    Prev
    Next
    INDEX
    Explanations

    geopolitical entities and their relationships, with a focus on international trade and political ties

    oai_token-act-pair · gpt-3.5-turbo

    geopolitical relationships and significant countries involved in international trade or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adobe
    -0.67
    mble
    -0.65
    ĨĴ
    -0.61
    Sym
    -0.60
    ãĥ£
    -0.57
    achine
    -0.56
     Plymouth
    -0.54
    maxwell
    -0.54
    etting
    -0.53
     chlorine
    -0.52
    POSITIVE LOGITS
    's
    0.75
     territory
    0.71
     shores
    0.66
     Stadium
    0.64
     Harbour
    0.62
     insofar
    0.61
     Airlines
    0.61
    anism
    0.61
     Oval
    0.60
    agi
    0.59
    Activations Density 0.400%

    No Known Activations