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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14287
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions related to Kurdish people or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Kurdish forces or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifax
    -0.83
    ottesville
    -0.79
    xual
    -0.78
    ysis
    -0.77
    urer
    -0.75
    ilogy
    -0.74
     Ago
    -0.72
    urers
    -0.70
    anson
    -0.70
    igne
    -0.69
    POSITIVE LOGITS
    istani
    1.38
     YPG
    0.95
     Kurdish
    0.91
     Pesh
    0.89
     militias
    0.89
     militia
    0.89
     Turks
    0.87
    merga
    0.87
     PKK
    0.86
     Kurds
    0.85
    Activations Density 0.010%

    No Known Activations