© 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. 10-RES-JB
    11. 8395
    Prev
    Next
    INDEX
    Explanations

    information related to policy decisions, government actions, and community development projects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Iran
    -0.96
    milo
    -0.75
     centrif
    -0.74
    CIA
    -0.74
     declass
    -0.73
    Australian
    -0.72
    Aust
    -0.71
    Intel
    -0.70
    Australia
    -0.69
    ython
    -0.69
    POSITIVE LOGITS
     mayoral
    1.88
     Mayor
    1.79
    Mayor
    1.78
     mayor
    1.75
     city
    1.69
     municipal
    1.68
     zoning
    1.64
     Downtown
    1.55
     City
    1.53
     Municipal
    1.53
    Activations Density 1.114%

    No Known Activations