© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12320
    Prev
    Next
    INDEX
    Explanations

    phrases discussing authority or control

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating possession or an association with a subject

    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
    0:0.06
    1:0.11
    2:0.11
    3:0.04
    4:0.08
    5:0.08
    6:0.07
    7:0.07
    8:0.15
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
    itaire
    -1.35
    mma
    -1.26
    iasm
    -1.17
    INESS
    -1.12
    advertisement
    -1.09
    addy
    -1.09
    wagon
    -1.08
    igers
    -1.07
    raq
    -1.04
    ouble
    -1.04
    POSITIVE LOGITS
     wearer
    1.28
    ーテ
    1.20
    pires
    1.07
    �
    1.03
    �
    1.03
     passers
    1.00
    independence
    0.99
     Bram
    0.97
     Roof
    0.96
     ancestor
    0.95
    Activations Density 0.189%

    No Known Activations