© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 35514
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be" and its variations, focusing on different contexts and tenses related to existence and state

    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
    0:0.21
    1:0.23
    2:0.04
    3:0.02
    4:0.02
    5:0.16
    6:0.03
    7:0.02
    8:0.09
    9:0.05
    10:0.03
    11:0.05
    Negative Logits
    machine
    -1.82
    plan
    -1.78
    wagen
    -1.75
    warm
    -1.69
    earth
    -1.66
    Thom
    -1.63
    nian
    -1.63
     Thom
    -1.61
    cube
    -1.61
    yan
    -1.58
    POSITIVE LOGITS
     discharged
    2.13
     stricken
    2.11
     assassinated
    2.08
     thrown
    2.08
     transferred
    1.95
    raught
    1.91
    Removed
    1.89
     Accessed
    1.88
     Referred
    1.83
     repealed
    1.82
    Activations Density 0.048%

    No Known Activations