© 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. 14365
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and technical concepts, specifically focusing on quantum materials, optical phenomena, and technological developments

    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
    0:0.07
    1:0.02
    2:0.27
    3:0.13
    4:0.03
    5:0.06
    6:0.02
    7:0.02
    8:0.09
    9:0.17
    10:0.04
    11:0.02
    Negative Logits
     omission
    -1.30
     Indust
    -1.29
    テ
    -1.26
     Auth
    -1.19
    tesy
    -1.17
    rities
    -1.17
     Paraly
    -1.15
     Orche
    -1.14
    actionDate
    -1.13
    MSN
    -1.12
    POSITIVE LOGITS
    asus
    1.43
    pun
    1.37
    yip
    1.23
    alon
    1.21
    entin
    1.21
    dos
    1.18
    ipe
    1.17
     zip
    1.17
     vape
    1.14
     loose
    1.14
    Activations Density 0.036%

    No Known Activations