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. 27492
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events

    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
    1:0.02
    2:0.09
    3:0.45
    4:0.06
    5:0.02
    6:0.02
    7:0.04
    8:0.05
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    inventoryQuantity
    -1.79
    ーティ
    -1.72
    isSpecialOrderable
    -1.60
    establishment
    -1.57
    ゴン
    -1.49
    WARE
    -1.41
    ":[{"
    -1.41
    annabin
    -1.41
    hab
    -1.40
     adolesc
    -1.34
    POSITIVE LOGITS
    .)
    4.58
    .)
    4.56
    .).
    4.52
    .")
    4.16
    ').
    4.13
    .),
    3.93
    ?).
    3.88
    .):
    3.85
    )."
    3.77
    .]
    3.75
    Activations Density 0.437%

    No Known Activations