© 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. 21097
    Prev
    Next
    INDEX
    Explanations

    numerical data related to income brackets and economic disparities

    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
    0:0.12
    1:0.05
    2:0.05
    3:0.27
    4:0.03
    5:0.15
    6:0.03
    7:0.05
    8:0.04
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
     villagers
    -1.92
     Okin
    -1.83
    onom
    -1.81
     peasants
    -1.80
     disadvantages
    -1.75
    ngth
    -1.75
     reperc
    -1.74
    opian
    -1.72
    ignty
    -1.72
    ingen
    -1.72
    POSITIVE LOGITS
    -$
    1.98
    200
    1.94
    .$
    1.94
    $,
    1.90
    /$
    1.85
    $
    1.83
    illion
    1.74
    riter
    1.68
     million
    1.66
    CLUD
    1.65
    Activations Density 0.018%

    No Known Activations