© 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. 804
    Prev
    Next
    INDEX
    Explanations

    terms associated with decision-making and the gathering of information

    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
    0:0.08
    1:0.10
    2:0.04
    3:0.06
    4:0.06
    5:0.05
    6:0.15
    7:0.03
    8:0.02
    9:0.32
    10:0.03
    11:0.01
    Negative Logits
     WD
    -3.49
    ams
    -3.46
     Dart
    -3.31
     tigers
    -3.27
     Judd
    -3.13
     Sequ
    -3.10
     Scal
    -3.05
     Vox
    -3.04
     Wax
    -3.00
    rub
    -2.99
    POSITIVE LOGITS
    information
    5.06
    Information
    4.77
     Information
    4.67
    info
    4.65
     informational
    4.52
    Info
    4.39
     information
    4.39
     INFORMATION
    4.35
     misinformation
    4.30
    INFO
    4.10
    Activations Density 0.003%

    No Known Activations