© 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. 20849
    Prev
    Next
    INDEX
    Explanations

    discourse markers and contextual phrases that indicate conversations, statements, or planning related to societal issues

    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
    0:0.09
    1:0.13
    2:0.07
    3:0.04
    4:0.03
    5:0.02
    6:0.19
    7:0.08
    8:0.02
    9:0.04
    10:0.21
    11:0.04
    Negative Logits
     Canaveral
    -2.96
     DPS
    -2.65
    ��
    -2.56
    fax
    -2.55
    weeney
    -2.53
     fructose
    -2.53
    ardy
    -2.52
     Spac
    -2.51
     sarc
    -2.48
     trooper
    -2.46
    POSITIVE LOGITS
     Ken
    8.86
    Ken
    8.80
     Kenya
    4.46
     Kenneth
    4.41
    KEN
    4.30
     Kenn
    4.13
    ken
    3.84
     Kenyan
    3.75
     Kent
    3.70
     Kin
    3.58
    Activations Density 0.013%

    No Known Activations