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. 2-ATT-KK
    6. 22303
    Prev
    Next
    INDEX
    Explanations

    phrases related to steady states or consistent flows in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.13
    3:0.09
    4:0.18
    5:0.07
    6:0.02
    7:0.02
    8:0.11
    9:0.14
    10:0.05
    11:0.02
    Negative Logits
     Loft
    -1.26
     Maul
    -1.18
     Navajo
    -1.18
     MAC
    -1.12
     Khalid
    -1.12
     Grimoire
    -1.10
     Herrera
    -1.10
     Moy
    -1.09
    �醒
    -1.09
     specifically
    -1.09
    POSITIVE LOGITS
    izons
    1.48
    itiveness
    1.44
    ounters
    1.29
    iability
    1.27
     steadily
    1.26
     steady
    1.26
     uptake
    1.25
     upward
    1.22
    hement
    1.22
    cean
    1.21
    Activations Density 0.005%

    No Known Activations