© 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. 3-ATT-KK
    11. 10733
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.04
    2:0.10
    3:0.12
    4:0.01
    5:0.02
    6:0.11
    7:0.07
    8:0.11
    9:0.20
    10:0.06
    11:0.10
    Negative Logits
     Deliver
    -1.05
    ーテ
    -1.02
    habi
    -1.01
    Cho
    -0.96
    bour
    -0.96
    ゴン
    -0.96
    legate
    -0.95
    orate
    -0.94
    peer
    -0.91
    egu
    -0.89
    POSITIVE LOGITS
     sake
    2.47
     purposes
    1.98
     reasons
    1.65
    ummies
    1.37
    ulz
    1.32
    icion
    1.30
     foreseeable
    1.27
    erity
    1.22
    izoph
    1.15
    iencies
    1.15
    Activations Density 0.078%

    No Known Activations