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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 7649
    Prev
    Next
    INDEX
    Explanations

    high-quality production techniques and their implications for product performance

    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
    0:0.09
    1:0.04
    2:0.09
    3:0.04
    4:0.06
    5:0.04
    6:0.23
    7:0.04
    8:0.07
    9:0.19
    10:0.03
    11:0.04
    Negative Logits
    anguage
    -4.04
    Hal
    -3.65
    ーン
    -3.62
    oké
    -3.48
    rador
    -3.46
    isoft
    -3.44
    án
    -3.38
    isphere
    -3.32
    ˈ
    -3.28
     membrane
    -3.24
    POSITIVE LOGITS
     Tw
    8.01
     TW
    7.95
    Tw
    7.31
    tw
    6.13
    TW
    5.80
     tw
    5.52
     Twist
    5.29
     Twisted
    5.26
     Twilight
    5.12
     Twin
    5.04
    Activations Density 0.004%

    No Known Activations