Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 2228
    Prev
    Next
    INDEX
    Explanations

    entities related to Turkish government officials

    oai_token-act-pair · gpt-3.5-turbo

    specific surnames and proper nouns, especially in the context of political figures or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ivy
    -0.83
     Hollywood
    -0.78
     Hearts
    -0.71
     Wonderland
    -0.65
     Harvard
    -0.64
     Kitty
    -0.64
     Candy
    -0.63
     Charisma
    -0.63
     Crusade
    -0.62
     Dartmouth
    -0.62
    POSITIVE LOGITS
    istani
    1.16
    ÄŁ
    1.15
    ı
    1.13
    oÄŁan
    1.03
    lu
    0.96
    rates
    0.95
    endar
    0.94
    uz
    0.93
    lish
    0.90
    ugal
    0.90
    Activations Density 0.010%

    No Known Activations