© 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. 4668
    Prev
    Next
    INDEX
    Explanations

    references to Italian entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Italian names and titles, particularly those starting with "Frances" or "C".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    proper names or entities from Italy

    oai_token-act-pair · gpt-3.5-turbo
    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
    keyes
    -0.82
     Shawn
    -0.81
     hive
    -0.80
     Bowman
    -0.80
     hemp
    -0.77
     Cherokee
    -0.76
    Bow
    -0.75
     tribal
    -0.75
     Yak
    -0.75
     Wyoming
    -0.74
    POSITIVE LOGITS
     Serie
    1.71
     Italy
    1.67
    Italy
    1.65
     Milan
    1.57
    Italian
    1.55
     Italian
    1.54
     Luigi
    1.54
     Juventus
    1.50
     Italians
    1.49
     Giovanni
    1.43
    Activations Density 0.477%

    No Known Activations