Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16243
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the European Union

    oai_token-act-pair · gpt-3.5-turbo

    references to European institutions and entities

    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
    enance
    -0.86
    chens
    -0.85
    runners
    -0.85
    acca
    -0.84
    elling
    -0.84
    LESS
    -0.81
    Downloadha
    -0.80
    ithing
    -0.79
    alach
    -0.77
    nels
    -0.75
    POSITIVE LOGITS
     Union
    1.46
     Parliament
    1.21
     Commission
    1.06
     nations
    0.90
     countries
    0.89
     Communities
    0.88
     Council
    0.88
     Monitoring
    0.87
     Economic
    0.87
     Federation
    0.87
    Activations Density 0.031%

    No Known Activations