© 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. 6395
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases associated with media, reports, and data releases

    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
    1:0.02
    2:0.04
    3:0.15
    4:0.03
    5:0.06
    6:0.02
    7:0.06
    8:0.03
    9:0.03
    10:0.41
    11:0.02
    Negative Logits
     guessed
    -2.24
     dearly
    -2.18
     prevailed
    -2.04
     prefers
    -2.04
    erest
    -2.01
    stood
    -2.01
     chuckled
    -1.99
     thri
    -1.99
     approached
    -1.97
     bothered
    -1.93
    POSITIVE LOGITS
     October
    2.38
     November
    2.36
    闘
    2.30
     April
    2.28
     amidst
    2.27
    ズ
    2.26
     February
    2.25
     January
    2.24
     yesterday
    2.23
     December
    2.23
    Activations Density 0.143%

    No Known Activations