© 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. 6643
    Prev
    Next
    INDEX
    Explanations

    numeric patterns or sequences, particularly in a format resembling phone numbers or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.32
    2:0.08
    3:0.11
    4:0.07
    5:0.10
    6:0.03
    7:0.04
    8:0.05
    9:0.04
    10:0.02
    11:0.03
    Negative Logits
     108
    -2.48
    auga
    -2.47
    htar
    -2.41
     Ake
    -2.40
    querade
    -2.35
     207
    -2.35
    ��
    -2.34
    abil
    -2.34
     107
    -2.33
    天
    -2.26
    POSITIVE LOGITS
     nearest
    2.49
    age
    2.31
    aunts
    2.19
    tips
    2.19
    aunt
    2.17
    letter
    2.14
    ages
    2.12
    Introduced
    2.11
     errone
    2.07
     assist
    2.07
    Activations Density 0.001%

    No Known Activations