© 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. 43786
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "be" and its various conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.09
    3:0.07
    4:0.05
    5:0.04
    6:0.15
    7:0.06
    8:0.03
    9:0.06
    10:0.15
    11:0.20
    Negative Logits
     Guam
    -1.37
    inventoryQuantity
    -1.36
    quickShipAvailable
    -1.34
     trailers
    -1.23
    urus
    -1.18
     Kardash
    -1.17
     forestry
    -1.12
     clauses
    -1.09
     forests
    -1.08
     primates
    -1.06
    POSITIVE LOGITS
    die
    1.43
    coe
    1.31
    semble
    1.29
    schild
    1.20
     hemor
    1.20
    icipated
    1.17
    aldi
    1.15
    oeuv
    1.15
    Die
    1.14
    ��
    1.14
    Activations Density 0.063%

    No Known Activations