© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 6165
    Prev
    Next
    INDEX
    Explanations

    discussions of economic inequality and social issues related to wealth distribution and its impact on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.08
    2:0.06
    3:0.03
    4:0.10
    5:0.21
    6:0.07
    7:0.05
    8:0.07
    9:0.04
    10:0.11
    11:0.05
    Negative Logits
     parody
    -1.77
     redacted
    -1.60
     english
    -1.57
     troll
    -1.47
     Birthday
    -1.47
     Verse
    -1.46
     birthday
    -1.44
     satire
    -1.44
    podcast
    -1.44
     titled
    -1.43
    POSITIVE LOGITS
     stagn
    1.99
     poorer
    1.97
     unsustainable
    1.89
     stagnant
    1.89
     trickle
    1.85
     impover
    1.84
     downstream
    1.84
     exacerb
    1.82
     populations
    1.81
     inefficient
    1.80
    Activations Density 0.734%

    No Known Activations