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. 15225
    Prev
    Next
    INDEX
    Explanations

    references to countries in conflict, particularly Syria and Iraq

    oai_token-act-pair · gpt-3.5-turbo

    references to conflict zones and countries affected by warfare

    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
     newsp
    -0.79
     glim
    -0.73
    issance
    -0.69
     ®
    -0.68
    ultimate
    -0.67
     largeDownload
    -0.67
    ¢
    -0.66
    geist
    -0.66
    MJ
    -0.65
     Chaser
    -0.65
    POSITIVE LOGITS
     Libya
    1.81
     Yemen
    1.75
     Somalia
    1.68
     Lebanon
    1.67
     Iraq
    1.63
     Sudan
    1.60
     Afghanistan
    1.58
     Tunisia
    1.52
     Algeria
    1.48
     Syria
    1.46
    Activations Density 0.113%

    No Known Activations