© 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. 5560
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with loss and familial connections

    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
    0:0.05
    1:0.01
    2:0.04
    3:0.20
    4:0.02
    5:0.08
    6:0.01
    7:0.06
    8:0.02
    9:0.01
    10:0.42
    11:0.02
    Negative Logits
    ーク
    -2.01
    rather
    -1.89
     alternatively
    -1.85
     suggestion
    -1.78
    dding
    -1.76
    ivably
    -1.69
     envisioned
    -1.68
    apers
    -1.67
    similar
    -1.67
    osite
    -1.66
    POSITIVE LOGITS
     due
    2.28
     because
    2.25
     :(
    2.02
     virginity
    1.99
     competitiveness
    1.93
     dearly
    1.88
    eto
    1.83
     owing
    1.81
    because
    1.75
    ashington
    1.70
    Activations Density 0.129%

    No Known Activations