© 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. 9-ATT-KK
    11. 416
    Prev
    Next
    INDEX
    Explanations

    instances of specific terms and expressions related to societal issues and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.04
    3:0.13
    4:0.07
    5:0.06
    6:0.11
    7:0.08
    8:0.05
    9:0.10
    10:0.14
    11:0.06
    Negative Logits
    Sullivan
    -3.11
     Juice
    -2.73
    osite
    -2.60
     Robinson
    -2.57
     Sullivan
    -2.57
     Brighton
    -2.56
    ovy
    -2.55
     Raymond
    -2.55
    uo
    -2.50
     Mole
    -2.49
    POSITIVE LOGITS
    �
    5.41
     �
    5.25
    ‎
    4.02
    †
    3.33
     «
    3.14
    �
    3.13
    vernment
    2.88
     pand
    2.87
    ■
    2.78
    �
    2.77
    Activations Density 0.175%

    No Known Activations