© 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. 10-ATT-KK
    11. 8587
    Prev
    Next
    INDEX
    Explanations

    information related to product analysis and performance evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.02
    2:0.02
    3:0.03
    4:0.07
    5:0.12
    6:0.01
    7:0.04
    8:0.02
    9:0.43
    10:0.01
    11:0.12
    Negative Logits
    版
    -2.69
     Methodist
    -2.45
     Doctors
    -2.40
    odcast
    -2.32
     Lobby
    -2.31
    emer
    -2.20
     assassinated
    -2.18
     Franch
    -2.10
    pired
    -2.09
     Protest
    -2.07
    POSITIVE LOGITS
    worthiness
    5.18
    ability
    5.02
     efficiency
    4.83
     effectiveness
    4.64
     accuracy
    4.57
     reliability
    4.46
     durability
    4.36
     availability
    4.35
    availability
    4.32
    fficiency
    4.25
    Activations Density 0.729%

    No Known Activations