© 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. 5-ATT-KK
    11. 25761
    Prev
    Next
    INDEX
    Explanations

    phrases indicating obligation or consequences related to actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.23
    3:0.06
    4:0.05
    5:0.04
    6:0.03
    7:0.03
    8:0.06
    9:0.06
    10:0.23
    11:0.13
    Negative Logits
    ciation
    -1.40
     mater
    -1.39
     Coyotes
    -1.31
     Scorp
    -1.29
     Mexicans
    -1.27
     mart
    -1.27
     lic
    -1.27
     garn
    -1.26
     regulation
    -1.26
     Grape
    -1.23
    POSITIVE LOGITS
    quickShipAvailable
    1.66
     beware
    1.60
     risked
    1.59
    uscript
    1.58
    :]
    1.57
     starve
    1.53
     evacuated
    1.45
     panicked
    1.44
     unwittingly
    1.43
    OHN
    1.41
    Activations Density 0.164%

    No Known Activations