© 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. 13521
    Prev
    Next
    INDEX
    Explanations

    phrases indicating investigation and scrutiny of marketing practices in the real estate sector

    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
    0:0.09
    1:0.03
    2:0.08
    3:0.05
    4:0.03
    5:0.04
    6:0.21
    7:0.04
    8:0.03
    9:0.26
    10:0.04
    11:0.04
    Negative Logits
    iHUD
    -3.57
     Atkinson
    -3.48
     Bed
    -3.42
     Ashes
    -3.39
     ash
    -3.37
     Dahl
    -3.34
    ====
    -3.29
     Mud
    -3.29
    Depth
    -3.29
    icken
    -3.25
    POSITIVE LOGITS
     prom
    6.81
     Prom
    6.70
     PR
    6.24
    prom
    5.95
     promo
    5.59
    Prom
    5.55
    PR
    5.37
     Marketing
    5.30
     promotional
    5.23
     Promotion
    5.19
    Activations Density 0.004%

    No Known Activations