© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 3685
    Prev
    Next
    INDEX
    Explanations

    mentions of specific cultural or political groups, particularly focusing on Kurdish units and forces

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Kurdish people and their military forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysis
    -0.80
    eus
    -0.77
    oeuv
    -0.76
    ertodd
    -0.74
    enment
    -0.74
    urer
    -0.73
    itud
    -0.73
    gio
    -0.71
    è¯
    -0.71
    ottesville
    -0.70
    POSITIVE LOGITS
    istani
    1.49
     Pesh
    1.05
     YPG
    0.99
     separatists
    0.92
     militias
    0.91
    merga
    0.88
     militia
    0.86
     PKK
    0.84
     separatist
    0.83
    istan
    0.82
    Activations Density 0.028%

    No Known Activations