© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 5777
    Prev
    Next
    INDEX
    Explanations

    the word "only" and its contextual relevance in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.08
    6:0.09
    7:0.07
    8:0.08
    9:0.09
    10:0.08
    11:0.08
    Negative Logits
     Bottle
    -2.61
     lvl
    -2.48
     quality
    -2.44
     Bott
    -2.35
     Supports
    -2.30
     Construct
    -2.27
     subst
    -2.27
     Cunning
    -2.12
     features
    -2.11
     deposit
    -2.07
    POSITIVE LOGITS
    ollah
    3.08
     ISIL
    3.03
    raged
    2.92
    Iraq
    2.89
     jihad
    2.87
     Iraqis
    2.84
    aq
    2.79
    タ
    2.75
    Arab
    2.74
     Baghdad
    2.73
    Activations Density 0.000%

    No Known Activations