© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 13349
    Prev
    Next
    INDEX
    Explanations

    the last names of notable people or historical figures, particularly names beginning with 'un' or 'Hark'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.03
    2:0.09
    3:0.04
    4:0.05
    5:0.06
    6:0.07
    7:0.14
    8:0.05
    9:0.04
    10:0.21
    11:0.12
    Negative Logits
     Kazakh
    -0.59
     DRAG
    -0.58
    jc
    -0.57
     charities
    -0.55
    FTWARE
    -0.53
    giving
    -0.53
     Kazakhstan
    -0.52
     alike
    -0.52
     weighing
    -0.51
    theless
    -0.51
    POSITIVE LOGITS
    EStream
    0.90
    uyomi
    0.60
    龍喚士
    0.60
    OVA
    0.58
    DragonMagazine
    0.57
     Bundy
    0.57
     裏�
    0.57
    otos
    0.56
    emort
    0.55
    iris
    0.55
    Activations Density 0.280%

    No Known Activations