© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-ATT-KK
    11. 22170
    Prev
    Next
    INDEX
    Explanations

    terms related to the postal service and delivery systems

    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
    0:0.30
    1:0.02
    2:0.12
    3:0.07
    4:0.03
    5:0.07
    6:0.06
    7:0.05
    8:0.05
    9:0.09
    10:0.03
    11:0.04
    Negative Logits
     OpenGL
    -2.95
    NVIDIA
    -2.91
    vidia
    -2.83
     TED
    -2.73
    amic
    -2.71
     Jonas
    -2.70
    etooth
    -2.69
    Developer
    -2.68
     NVIDIA
    -2.66
     Cyborg
    -2.66
    POSITIVE LOGITS
     postal
    7.04
     USPS
    6.33
     Postal
    6.29
     mail
    5.64
     postage
    5.41
     Mail
    4.99
     stamps
    4.88
     mailbox
    4.75
     mailing
    4.52
    Mail
    4.40
    Activations Density 0.025%

    No Known Activations