© 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. 7-RES-JB
    11. 15354
    Prev
    Next
    INDEX
    Explanations

    mentions of the European Union

    oai_token-act-pair · gpt-3.5-turbo

    references to the European Union or related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    runners
    -0.91
    chens
    -0.88
    Downloadha
    -0.86
    elling
    -0.83
    veland
    -0.83
    LESS
    -0.82
    ithing
    -0.81
    alach
    -0.81
    enance
    -0.81
    reads
    -0.81
    POSITIVE LOGITS
     Union
    1.40
     Parliament
    1.20
     Commission
    1.04
     nations
    0.94
     countries
    0.92
     Federation
    0.89
     Integration
    0.88
     Communities
    0.88
     Stability
    0.86
     parliament
    0.85
    Activations Density 0.026%

    No Known Activations