© 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. 3-ATT-KK
    11. 9363
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and recognition for leadership and community involvement

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

    No Comments

    Head Attr Weights
    0:0.04
    1:0.08
    2:0.08
    3:0.04
    4:0.08
    5:0.16
    6:0.07
    7:0.08
    8:0.10
    9:0.06
    10:0.09
    11:0.07
    Negative Logits
     retracted
    -1.43
     initials
    -1.29
    ighed
    -1.27
    Poké
    -1.26
    Accessory
    -1.23
     unrelated
    -1.21
    sheet
    -1.21
     incrim
    -1.20
    Adds
    -1.19
    arov
    -1.18
    POSITIVE LOGITS
    erity
    1.86
    ankind
    1.56
     JUSTICE
    1.44
     oppressed
    1.35
    kefeller
    1.34
     Genocide
    1.33
     trillions
    1.32
     yourselves
    1.31
     tyranny
    1.29
     SERV
    1.29
    Activations Density 0.642%

    No Known Activations