© 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. 3-ATT-KK
    11. 8090
    Prev
    Next
    INDEX
    Explanations

    negative modifiers and the concept of quality or integrity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.03
    2:0.14
    3:0.17
    4:0.02
    5:0.02
    6:0.17
    7:0.11
    8:0.07
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
    ependence
    -1.21
    umption
    -1.18
    ��
    -1.18
    itivity
    -1.15
    anooga
    -1.12
    ivalry
    -1.10
    itu
    -1.10
    itational
    -1.08
    Wik
    -1.06
    ipation
    -1.05
    POSITIVE LOGITS
     toile
    1.15
     incarn
    1.09
     fodder
    1.00
    theless
    0.96
     Gleaming
    0.95
     tempered
    0.94
    med
    0.94
    arin
    0.93
     soluble
    0.91
    arters
    0.91
    Activations Density 0.292%

    No Known Activations