© 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. 9-ATT-KK
    11. 23072
    Prev
    Next
    INDEX
    Explanations

    themes related to economic inequality and the disparity between rich and poor

    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
    0:0.04
    1:0.05
    2:0.05
    3:0.08
    4:0.05
    5:0.11
    6:0.07
    7:0.37
    8:0.05
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
    ertodd
    -2.68
    zees
    -2.33
    xus
    -2.23
     hangar
    -2.15
     Paddock
    -2.14
    roleum
    -2.11
    phies
    -2.08
    stasy
    -2.07
    uca
    -2.06
    osterone
    -2.05
    POSITIVE LOGITS
     poor
    3.01
    五
    2.85
    0010
    2.84
     poorest
    2.72
    ク
    2.71
    poor
    2.59
    democracy
    2.56
     poorer
    2.40
     democratic
    2.40
    democratic
    2.32
    Activations Density 0.035%

    No Known Activations