© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 9487
    Prev
    Next
    INDEX
    Explanations

    phrases and structures related to discussions of public and private sectors, particularly in legislative or regulatory contexts

    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
    1:0.10
    2:0.03
    3:0.05
    4:0.07
    5:0.03
    6:0.05
    7:0.39
    8:0.02
    9:0.04
    10:0.04
    11:0.09
    Negative Logits
    NW
    -2.71
    MON
    -2.46
    Norm
    -2.42
    tracking
    -2.27
     Vern
    -2.21
     mete
    -2.17
     Nether
    -2.15
    DON
    -2.15
     Naj
    -2.11
    Parents
    -2.07
    POSITIVE LOGITS
     Dagger
    2.75
    lasses
    2.64
    ドラ
    2.61
    ertodd
    2.61
    laus
    2.61
    appa
    2.56
     lightsaber
    2.56
    agi
    2.53
    ze
    2.51
     CLSID
    2.49
    Activations Density 0.020%

    No Known Activations