© 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. 10-ATT-KK
    11. 14161
    Prev
    Next
    INDEX
    Explanations

    references to world records or record-breaking events

    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
    0:0.08
    1:0.03
    2:0.04
    3:0.04
    4:0.05
    5:0.03
    6:0.09
    7:0.20
    8:0.03
    9:0.17
    10:0.03
    11:0.15
    Negative Logits
     Webb
    -2.58
     Romeo
    -2.41
     Biden
    -2.28
     Sieg
    -2.24
     Boehner
    -2.24
     antit
    -2.24
     BDS
    -2.15
    Iv
    -2.12
     runoff
    -2.12
     BlackBerry
    -2.11
    POSITIVE LOGITS
    electric
    2.48
    valid
    2.42
     Passenger
    2.37
    operator
    2.28
    ilers
    2.15
    �
    2.15
     Places
    2.15
    feet
    2.14
    ック
    2.14
    omical
    2.10
    Activations Density 0.000%

    No Known Activations