© 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. 15004
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reflections on past events or actions

    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
    0:0.23
    1:0.15
    2:0.14
    3:0.04
    4:0.04
    5:0.02
    6:0.05
    7:0.12
    8:0.06
    9:0.02
    10:0.06
    11:0.01
    Negative Logits
     Browne
    -3.31
     Blackburn
    -3.18
     Cherokee
    -3.13
     Lanc
    -3.12
     Shelby
    -3.08
     Chero
    -3.07
     Watkins
    -3.04
     Dominican
    -3.03
     Tripoli
    -3.01
     Preston
    -3.01
    POSITIVE LOGITS
    å
    4.34
    ø
    4.07
    �
    3.79
    �
    3.71
    д
    3.64
     �
    3.52
     Veh
    3.50
    】
    3.46
    û
    3.44
    �
    3.42
    Activations Density 0.131%

    No Known Activations