Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27601
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and its various conjugations

    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
    0:0.17
    1:0.35
    2:0.05
    3:0.03
    4:0.02
    5:0.14
    6:0.03
    7:0.02
    8:0.05
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
    κ
    -1.82
    iss
    -1.82
     Tud
    -1.78
    vill
    -1.78
    551
    -1.76
    681
    -1.75
    ghai
    -1.73
    �
    -1.71
    651
    -1.66
    jong
    -1.60
    POSITIVE LOGITS
    been
    2.38
     been
    2.06
     Been
    2.04
     afore
    1.78
    hare
    1.77
     embodied
    1.75
    ��
    1.75
     awa
    1.74
     Beetle
    1.71
     ridden
    1.70
    Activations Density 0.006%

    No Known Activations