© 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. 10-ATT-KK
    11. 21802
    Prev
    Next
    INDEX
    Explanations

    topics related to basic needs and services affecting vulnerable populations

    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
    0:0.03
    1:0.03
    2:0.04
    3:0.07
    4:0.09
    5:0.24
    6:0.04
    7:0.05
    8:0.02
    9:0.26
    10:0.02
    11:0.06
    Negative Logits
    Edited
    -2.91
    actly
    -2.56
    iannopoulos
    -2.42
     Wrong
    -2.42
    arted
    -2.37
     idiots
    -2.36
     Stupid
    -2.27
    opped
    -2.23
    javascript
    -2.23
     Klux
    -2.23
    POSITIVE LOGITS
     because
    2.90
     due
    2.89
     anymore
    2.79
     financially
    2.76
     ensures
    2.65
     thanks
    2.65
     helps
    2.61
     upkeep
    2.52
     keeps
    2.52
     coping
    2.50
    Activations Density 0.162%

    No Known Activations