© 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. 10-ATT-KK
    11. 21005
    Prev
    Next
    INDEX
    Explanations

    terms related to economic suffering and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.04
    2:0.03
    3:0.05
    4:0.11
    5:0.04
    6:0.03
    7:0.12
    8:0.02
    9:0.16
    10:0.03
    11:0.26
    Negative Logits
     COUR
    -2.09
    ecided
    -2.08
    Ready
    -2.07
     Loaded
    -2.07
    interested
    -2.06
     Gim
    -2.04
     actors
    -1.97
    ONSORED
    -1.81
     exerc
    -1.80
    emouth
    -1.79
    POSITIVE LOGITS
     degradation
    2.72
     blackout
    2.48
     woes
    2.48
     disruptions
    2.47
     renaissance
    2.43
     suffer
    2.43
     setbacks
    2.42
     crippling
    2.41
     losses
    2.41
    loss
    2.39
    Activations Density 0.029%

    No Known Activations