© 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. 5-ATT-KK
    11. 40989
    Prev
    Next
    INDEX
    Explanations

    references to singular indefinite articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.11
    3:0.07
    4:0.15
    5:0.03
    6:0.25
    7:0.06
    8:0.04
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
    flag
    -1.47
    mother
    -1.43
     HP
    -1.42
     Pt
    -1.40
    adr
    -1.36
     Purple
    -1.34
     Physical
    -1.33
    Father
    -1.33
    Knight
    -1.32
     Papa
    -1.31
    POSITIVE LOGITS
    umerable
    1.94
    �
    1.74
     ende
    1.73
    iencies
    1.70
    aunder
    1.64
     sqor
    1.56
    WARE
    1.55
     resear
    1.53
    ukong
    1.52
    iott
    1.52
    Activations Density 0.000%

    No Known Activations