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

    Neuronpedia

    Jacobian LensNEW
    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. 12345
    Prev
    Next
    INDEX
    Explanations

    references to the Kurdish Peshmerga forces

    oai_token-act-pair · gpt-3.5-turbo

    references to Kurdish Peshmerga fighters and related statements

    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
     Benson
    -0.66
     funnel
    -0.65
    rame
    -0.63
     Marion
    -0.62
     binge
    -0.61
    ^{
    -0.60
    andon
    -0.60
     Hou
    -0.60
    Frame
    -0.59
    ueller
    -0.59
    POSITIVE LOGITS
     Pesh
    4.40
     KR
    1.50
     Karachi
    1.47
     Lah
    1.43
     Islamabad
    1.35
    KR
    1.33
     Kabul
    1.19
     Kash
    1.18
     KP
    1.16
     Sind
    1.14
    Activations Density 0.034%

    No Known Activations