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. 0-RES-JB
    6. 5724
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Robert."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Robert."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     messenger
    -0.83
    chat
    -0.74
     Messenger
    -0.74
    Desktop
    -0.71
     WhatsApp
    -0.70
     upgr
    -0.70
    8000
    -0.70
    bike
    -0.69
    âĸĪ
    -0.69
    Phones
    -0.69
    POSITIVE LOGITS
     Robert
    3.10
    Robert
    2.78
     Kenneth
    1.78
     Richard
    1.74
     William
    1.66
     Ronald
    1.58
     Roger
    1.56
     Philip
    1.55
     Walter
    1.53
     Christopher
    1.50
    Activations Density 0.018%

    No Known Activations