© 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. 12659
    Prev
    Next
    INDEX
    Explanations

    references to events and their scheduling

    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
    0:0.06
    1:0.03
    2:0.08
    3:0.13
    4:0.13
    5:0.13
    6:0.04
    7:0.07
    8:0.04
    9:0.14
    10:0.04
    11:0.06
    Negative Logits
     denies
    -2.68
     discredited
    -2.61
     disputed
    -2.57
     deny
    -2.55
     antit
    -2.47
     improperly
    -2.47
     disav
    -2.45
     falsely
    -2.43
     undermines
    -2.37
     neglig
    -2.36
    POSITIVE LOGITS
     🙂
    3.74
    Yesterday
    3.22
     haha
    3.15
     �
    3.12
    iversary
    3.02
    ~~
    2.90
    ~
    2.89
    Â
    2.88
    oooo
    2.80
    estern
    2.78
    Activations Density 0.516%

    No Known Activations