© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21829
    Prev
    Next
    INDEX
    Explanations

    references to individuals with specific professional or personal identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.03
    3:0.04
    4:0.08
    5:0.37
    6:0.02
    7:0.03
    8:0.01
    9:0.29
    10:0.01
    11:0.03
    Negative Logits
     VIDEOS
    -2.92
    onies
    -2.77
     ACTIONS
    -2.67
     Invalid
    -2.62
    Instead
    -2.48
     IMAGES
    -2.46
     suffice
    -2.43
     Instead
    -2.35
    ={
    -2.33
    rompt
    -2.31
    POSITIVE LOGITS
    who
    3.97
     who
    3.81
     whose
    3.78
     whom
    3.60
    whose
    3.59
     formerly
    3.36
     specializing
    3.07
     currently
    2.72
     residing
    2.64
     avid
    2.60
    Activations Density 0.376%

    No Known Activations