© 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. 9-ATT-KK
    11. 18554
    Prev
    Next
    INDEX
    Explanations

    references to stability and performance issues in systems or processes

    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
    0:0.07
    1:0.04
    2:0.12
    3:0.05
    4:0.05
    5:0.04
    6:0.23
    7:0.04
    8:0.05
    9:0.20
    10:0.03
    11:0.03
    Negative Logits
     Mei
    -4.50
     Pai
    -4.45
     Pepsi
    -4.17
     Ping
    -3.87
     Phelps
    -3.85
     Dunham
    -3.75
     Hog
    -3.60
     Harbaugh
    -3.55
     Egg
    -3.54
     Zhou
    -3.48
    POSITIVE LOGITS
    stable
    6.66
     unstable
    6.37
     stable
    6.36
     stability
    6.32
     instability
    6.24
     stabil
    6.18
     Stability
    6.11
     stabilize
    6.03
     stabilization
    5.82
     stabilized
    5.59
    Activations Density 0.001%

    No Known Activations