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

    Neuronpedia

    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. 5-ATT-KK
    11. 7614
    Prev
    Next
    INDEX
    Explanations

    references to names or terms related to notable individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.04
    3:0.06
    4:0.04
    5:0.05
    6:0.40
    7:0.07
    8:0.05
    9:0.07
    10:0.07
    11:0.04
    Negative Logits
    Downloadha
    -1.57
     legitimately
    -1.39
     assets
    -1.29
     Finnish
    -1.23
    esthetic
    -1.22
     duct
    -1.21
     veins
    -1.20
    asking
    -1.19
     delegation
    -1.17
     shaping
    -1.17
    POSITIVE LOGITS
    ��
    1.60
    jong
    1.52
    י
    1.35
    rand
    1.34
    Royal
    1.33
    Prin
    1.33
    urga
    1.32
    �士
    1.30
    lang
    1.30
    bad
    1.30
    Activations Density 0.003%

    No Known Activations