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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4216
    Prev
    Next
    INDEX
    Explanations

    mentions of Italian businessmen and relevant financial activities

    oai_token-act-pair · gpt-3.5-turbo

    references to Italian people or entities, particularly in business and sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     KH
    -1.13
    Kim
    -1.01
    HB
    -0.93
     Winnipeg
    -0.92
     hive
    -0.91
     Hunts
    -0.91
    nw
    -0.89
    Haw
    -0.88
    Bow
    -0.87
    KING
    -0.86
    POSITIVE LOGITS
    Italy
    2.18
     Italians
    2.15
     Italy
    2.14
     Italian
    2.10
     Serie
    2.01
    Italian
    2.00
     Milan
    1.99
     Giul
    1.94
     Aless
    1.87
     Giovanni
    1.83
    Activations Density 0.664%

    No Known Activations