© 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. 9-ATT-KK
    11. 1050
    Prev
    Next
    INDEX
    Explanations

    expressions related to media influence and engagement

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.04
    4:0.08
    5:0.05
    6:0.17
    7:0.07
    8:0.12
    9:0.24
    10:0.02
    11:0.04
    Negative Logits
     Romero
    -3.97
     NASL
    -3.50
     dome
    -3.30
     Ner
    -3.26
    Kay
    -3.24
    omnia
    -3.23
     Omn
    -3.19
     Tent
    -3.19
     Ober
    -3.10
     Mord
    -3.09
    POSITIVE LOGITS
     China
    8.45
    China
    8.05
     Chinese
    8.03
    Chinese
    7.62
     Beijing
    7.61
     Xi
    7.40
     Shanghai
    6.75
     Xin
    6.64
    ijing
    6.63
    Xi
    6.32
    Activations Density 0.076%

    No Known Activations