© 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. 14539
    Prev
    Next
    INDEX
    Explanations

    instances of the word "been"

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

    repeated instances of the word "been" 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
    0:0.03
    1:0.03
    2:0.08
    3:0.06
    4:0.03
    5:0.05
    6:0.11
    7:0.06
    8:0.11
    9:0.17
    10:0.17
    11:0.05
    Negative Logits
    anova
    -0.99
    =$
    -0.92
    incinn
    -0.90
    imei
    -0.87
    zac
    -0.82
    zan
    -0.82
    vised
    -0.78
     consent
    -0.77
     eligibility
    -0.76
    velt
    -0.76
    POSITIVE LOGITS
     Brach
    0.83
     lately
    0.82
    pmwiki
    0.81
    natureconservancy
    0.81
    letal
    0.79
    @#&
    0.78
     "$:/
    0.76
    eries
    0.75
     Rear
    0.75
    kell
    0.74
    Activations Density 0.114%

    No Known Activations