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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20083
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical figures and royalty from different countries

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures and their relationships

    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
     skate
    -0.87
     taco
    -0.86
    FOX
    -0.85
    yz
    -0.82
    baugh
    -0.82
     pickup
    -0.80
    Magikarp
    -0.80
     MLS
    -0.80
     nood
    -0.78
     Sounders
    -0.78
    POSITIVE LOGITS
     Eleanor
    1.74
     Duchess
    1.65
     Princess
    1.55
     Buckingham
    1.53
     Catherine
    1.53
     Diana
    1.52
     Margaret
    1.50
     Queen
    1.46
     Anne
    1.45
     Elizabeth
    1.43
    Activations Density 0.392%

    No Known Activations