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

    Neuronpedia

    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. 2781
    Prev
    Next
    INDEX
    Explanations

    pieces of technical information, particularly related to computer programming and data management

    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
    0:0.07
    1:0.10
    2:0.07
    3:0.13
    4:0.07
    5:0.07
    6:0.05
    7:0.08
    8:0.04
    9:0.04
    10:0.04
    11:0.18
    Negative Logits
     Telesc
    -3.08
     Bows
    -3.03
     Balls
    -2.97
     Clo
    -2.94
     Drops
    -2.83
     Haste
    -2.82
     Chains
    -2.81
     Cruise
    -2.80
     Secrets
    -2.79
     Sur
    -2.78
    POSITIVE LOGITS
     tex
    3.19
     factor
    3.01
     entity
    2.92
     denomin
    2.92
     identifier
    2.84
     locale
    2.81
     macro
    2.80
     workspace
    2.80
     inhibitor
    2.75
     label
    2.74
    Activations Density 0.016%

    No Known Activations