© 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. 5-ATT-KK
    11. 27102
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" in various contexts

    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
    0:0.05
    1:0.04
    2:0.10
    3:0.08
    4:0.12
    5:0.05
    6:0.06
    7:0.18
    8:0.04
    9:0.05
    10:0.08
    11:0.10
    Negative Logits
     Employment
    -1.30
     foes
    -1.30
     GOT
    -1.29
     CIS
    -1.29
     unwelcome
    -1.26
     DS
    -1.24
     bunch
    -1.23
     defending
    -1.21
     outright
    -1.20
     opposition
    -1.18
    POSITIVE LOGITS
    ionic
    1.74
    aqu
    1.69
    ocrates
    1.68
    cean
    1.58
    arta
    1.57
    autical
    1.55
    inventoryQuantity
    1.52
     Parables
    1.50
    武
    1.37
    DragonMagazine
    1.37
    Activations Density 0.000%

    No Known Activations