© 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. 10-ATT-KK
    11. 6774
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential future actions or decisions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.08
    3:0.08
    4:0.06
    5:0.04
    6:0.18
    7:0.13
    8:0.03
    9:0.06
    10:0.08
    11:0.05
    Negative Logits
     bashing
    -2.32
    cial
    -2.32
     Appro
    -2.31
     rall
    -2.25
    .):
    -2.22
     projecting
    -2.21
     Bret
    -2.17
    Build
    -2.15
    Beta
    -2.14
    arter
    -2.14
    POSITIVE LOGITS
     Rowling
    2.92
     Sanders
    2.88
    iku
    2.65
    Herm
    2.59
     Hermes
    2.55
     Hermione
    2.54
    urga
    2.52
     Hogwarts
    2.51
     Granger
    2.49
     Potter
    2.49
    Activations Density 0.001%

    No Known Activations