© 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. 1263
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to updates and releases in a system or product

    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
    0:0.14
    1:0.03
    2:0.11
    3:0.05
    4:0.04
    5:0.06
    6:0.18
    7:0.04
    8:0.10
    9:0.16
    10:0.03
    11:0.02
    Negative Logits
     Swanson
    -4.02
     Kramer
    -3.48
    ecast
    -3.44
     Mous
    -3.25
     Comedy
    -3.22
     Liter
    -3.17
     Serv
    -3.14
     Uri
    -3.13
    Cart
    -3.13
     Stevenson
    -3.12
    POSITIVE LOGITS
     patch
    8.85
     Patch
    8.24
     patches
    8.21
    patch
    8.18
    Patch
    8.05
     patched
    7.65
    pat
    4.67
     Reaper
    3.88
    Pat
    3.81
    Sov
    3.63
    Activations Density 0.006%

    No Known Activations