© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 2131
    Prev
    Next
    INDEX
    Explanations

    mentions of German-related entities or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to Germany or things associated with German culture or identity

    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
     Pavilion
    -0.72
     Hawkins
    -0.67
    LV
    -0.66
    ILA
    -0.65
    Array
    -0.65
    reach
    -0.64
     Tray
    -0.63
     Avatar
    -0.63
     nominate
    -0.63
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.62
    POSITIVE LOGITS
     German
    3.53
    German
    3.23
     Germans
    2.85
    Germany
    2.42
     Germany
    2.42
     Hungarian
    2.26
     Polish
    2.23
     Belgian
    2.21
     Swedish
    2.17
     Danish
    2.16
    Activations Density 0.033%

    No Known Activations