© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18556
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts related to significant events and changes in bodies of water

    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
    0:0.06
    1:0.02
    2:0.04
    3:0.03
    4:0.06
    5:0.03
    6:0.34
    7:0.04
    8:0.07
    9:0.23
    10:0.01
    11:0.03
    Negative Logits
    hex
    -3.68
     microw
    -3.56
    Shin
    -3.49
     MK
    -3.42
     Wiz
    -3.40
     cand
    -3.35
     Ike
    -3.34
     Hang
    -3.25
     Hammond
    -3.24
     Shin
    -3.23
    POSITIVE LOGITS
    River
    10.89
     Rivera
    9.49
     River
    8.76
    river
    8.63
     river
    8.30
     Rivers
    7.60
     rivers
    6.98
     waterfall
    5.30
     waterways
    5.26
     creek
    5.18
    Activations Density 0.007%

    No Known Activations