© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10242
    Prev
    Next
    INDEX
    Explanations

    the definite article "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.09
    2:0.03
    3:0.12
    4:0.07
    5:0.12
    6:0.09
    7:0.06
    8:0.03
    9:0.16
    10:0.05
    11:0.02
    Negative Logits
    ================
    -2.57
    IRC
    -2.46
    ERC
    -2.40
     Quant
    -2.34
    loads
    -2.29
    ese
    -2.29
    �
    -2.25
     Browser
    -2.23
     Clicker
    -2.22
     Satisf
    -2.18
    POSITIVE LOGITS
    Sov
    2.40
     Soviets
    2.35
     IU
    2.32
     IB
    2.28
    boa
    2.24
    ivas
    2.18
    oran
    2.17
     Valiant
    2.17
    unda
    2.16
    beam
    2.13
    Activations Density 0.000%

    No Known Activations