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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 9207
    Prev
    Next
    INDEX
    Explanations

    political terms related to Serbia

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities and leadership in a specific geographical context

    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
    Oak
    -1.13
    Houston
    -1.08
    Hamilton
    -1.04
    Hong
    -0.99
     Xie
    -0.98
    Texas
    -0.97
     Harvey
    -0.96
     Texans
    -0.88
     Hamilton
    -0.88
    Austin
    -0.83
    POSITIVE LOGITS
     Serbian
    2.40
     Croatian
    2.35
     Serbia
    2.30
     Croatia
    2.29
     Croat
    2.17
     Kosovo
    2.15
     Yugoslav
    2.13
     Monteneg
    2.09
     Bosnia
    2.05
    Äĩ
    2.03
    Activations Density 0.245%

    No Known Activations