© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18380
    Prev
    Next
    INDEX
    Explanations

    government department names and related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to government departments and their activities

    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
     globally
    -0.85
     worldwide
    -0.84
     domestically
    -0.80
     slogans
    -0.78
     queries
    -0.74
     geop
    -0.72
     Afghans
    -0.72
     globalization
    -0.71
     embodiments
    -0.69
     chants
    -0.67
    POSITIVE LOGITS
    bernatorial
    1.11
     Legislature
    1.06
    istrate
    0.91
     Penal
    0.89
     District
    0.88
    istrates
    0.88
     Veter
    0.86
     legislature
    0.86
     Militia
    0.85
     Registry
    0.85
    Activations Density 0.182%

    No Known Activations