© 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. 9-RES-JB
    6. 16629
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic meetings or negotiations between countries

    oai_token-act-pair · gpt-3.5-turbo

    references to international relations and meetings between country leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,,,,
    -0.86
    %,
    -0.80
    ,,,,,,,,
    -0.69
    ?,
    -0.68
    %;
    -0.68
    \\
    -0.67
    ????????
    -0.66
     bc
    -0.65
    ,...
    -0.65
    ,,
    -0.65
    POSITIVE LOGITS
    pmwiki
    0.66
    etheless
    0.63
     hindsight
    0.58
     policymakers
    0.58
     caveats
    0.55
     Politico
    0.55
     diplomatic
    0.52
     rhetorical
    0.52
     decidedly
    0.51
     discussions
    0.51
    Activations Density 1.528%

    No Known Activations