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. 11-RES-JB
    6. 11023
    Prev
    Next
    INDEX
    Explanations

    sentences discussing historical events and legal settlements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference government actions or political declarations

    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
     Hyundai
    -0.92
     è£ıè
    -0.84
     crib
    -0.80
     lich
    -0.80
    undai
    -0.79
     Slovenia
    -0.79
     Zer
    -0.78
    uala
    -0.78
    orsche
    -0.78
    æł
    -0.78
    POSITIVE LOGITS
     Adams
    2.65
    Adams
    2.49
     Armstrong
    1.37
     Barton
    1.33
     Dock
    1.09
     Ballard
    1.06
     Jennings
    1.06
     Bates
    1.03
     Russell
    1.00
     Bond
    1.00
    Activations Density 0.115%

    No Known Activations