© 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. 6301
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing or withholding information, particularly in context of details, estimates, and discussions

    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
    1:0.02
    2:0.06
    3:0.18
    4:0.04
    5:0.09
    6:0.02
    7:0.06
    8:0.04
    9:0.02
    10:0.34
    11:0.02
    Negative Logits
     Nurs
    -1.93
     Created
    -1.90
     dreams
    -1.89
     EVERY
    -1.88
    pires
    -1.84
     ());
    -1.81
     Badge
    -1.79
     badass
    -1.79
     Syndrome
    -1.77
    ());
    -1.76
    POSITIVE LOGITS
     specifics
    3.42
     nor
    3.07
     details
    2.85
     particulars
    2.78
     divul
    2.63
    nor
    2.58
     elabor
    2.58
     explanation
    2.57
     detail
    2.56
     explain
    2.52
    Activations Density 0.152%

    No Known Activations