© 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. 3-ATT-KK
    11. 14375
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repeated actions or occurrences

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    the repetition of the word "again" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.15
    3:0.16
    4:0.02
    5:0.03
    6:0.12
    7:0.10
    8:0.07
    9:0.07
    10:0.10
    11:0.07
    Negative Logits
    ��
    -1.28
     Merchant
    -1.26
    imum
    -1.25
    CAP
    -1.18
     Mixed
    -1.14
    ersed
    -1.11
    tained
    -1.05
     Mald
    -1.04
     Flag
    -1.02
     Cape
    -1.02
    POSITIVE LOGITS
     inconsist
    1.33
     vig
    1.29
     failings
    1.18
     misogyny
    1.16
     frustrations
    1.12
     tendencies
    1.10
     faults
    1.09
    ppo
    1.09
     humili
    1.07
    vous
    1.06
    Activations Density 0.001%

    No Known Activations