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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11384
    Prev
    Next
    INDEX
    Explanations

    mentions of Microsoft and its products or updates

    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
    0:0.18
    1:0.01
    2:0.06
    3:0.09
    4:0.02
    5:0.08
    6:0.03
    7:0.05
    8:0.35
    9:0.03
    10:0.02
    11:0.02
    Negative Logits
    Cruz
    -3.67
     Jagu
    -3.41
     Flores
    -3.40
     Cruz
    -3.39
    ğ
    -3.33
     Wichita
    -3.28
     Lancaster
    -3.19
    idad
    -3.13
     Venezuelan
    -3.02
     Maduro
    -3.02
    POSITIVE LOGITS
     Cortana
    7.11
     Kinect
    6.86
     Microsoft
    6.45
    Microsoft
    6.07
     Xbox
    5.80
     Lumia
    5.59
     Redmond
    5.43
     Windows
    5.36
    Xbox
    5.28
     Azure
    5.18
    Activations Density 0.090%

    No Known Activations