© 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. 17156
    Prev
    Next
    INDEX
    Explanations

    phrases related to liquid substances and their physical forms

    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
    0:0.08
    1:0.04
    2:0.06
    3:0.06
    4:0.06
    5:0.05
    6:0.24
    7:0.05
    8:0.04
    9:0.20
    10:0.04
    11:0.03
    Negative Logits
    anny
    -4.10
     Randall
    -4.01
     Scare
    -3.76
     Timbers
    -3.68
     Runes
    -3.64
     Sage
    -3.60
     Chamberlain
    -3.48
     Guild
    -3.40
     Randolph
    -3.35
     Barbarian
    -3.29
    POSITIVE LOGITS
     liquid
    7.28
     Liquid
    7.13
    Liquid
    7.00
    liquid
    6.75
     liquids
    6.32
     fluid
    5.61
    iquid
    5.50
    Solid
    5.05
    solid
    4.91
     fluids
    4.65
    Activations Density 0.005%

    No Known Activations