© 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. 9-ATT-KK
    11. 4649
    Prev
    Next
    INDEX
    Explanations

    specific references to promotional events or discounts

    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
    0:0.06
    1:0.02
    2:0.11
    3:0.31
    4:0.03
    5:0.11
    6:0.01
    7:0.09
    8:0.03
    9:0.01
    10:0.14
    11:0.02
    Negative Logits
     contradicted
    -2.22
     coercive
    -2.13
     declined
    -2.11
    errors
    -2.00
     objected
    -1.98
     derog
    -1.98
     spurious
    -1.94
     refuted
    -1.93
     intermedi
    -1.92
     suicides
    -1.90
    POSITIVE LOGITS
     yours
    2.83
     stylish
    2.79
     delicious
    2.74
     unforgettable
    2.72
     gorgeous
    2.70
     YOUR
    2.68
     delight
    2.65
     pleasure
    2.60
    Enjoy
    2.59
     yourself
    2.57
    Activations Density 1.101%

    No Known Activations