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. 10-RES-JB
    6. 8963
    Prev
    Next
    INDEX
    Explanations

    German-related entities and names

    oai_token-act-pair · gpt-3.5-turbo

    references to German newspapers and media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coral
    -1.00
     Baton
    -0.91
     Mississ
    -0.91
     Korra
    -0.90
     Cherokee
    -0.87
     Roku
    -0.87
     Louisiana
    -0.86
     Mayweather
    -0.86
     Navajo
    -0.84
     coconut
    -0.83
    POSITIVE LOGITS
     Bundes
    1.99
     Germany
    1.88
    Germany
    1.86
     Bundesliga
    1.83
     German
    1.82
     Munich
    1.80
     Mü
    1.79
     Berlin
    1.76
     Merkel
    1.75
     Cologne
    1.74
    Activations Density 0.832%

    No Known Activations