© 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 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. 22081
    Prev
    Next
    INDEX
    Explanations

    plans and future developments related to technology and applications

    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
    0:0.12
    1:0.03
    2:0.14
    3:0.12
    4:0.03
    5:0.12
    6:0.03
    7:0.04
    8:0.03
    9:0.02
    10:0.22
    11:0.04
    Negative Logits
     disappointment
    -1.95
     resignation
    -1.94
     Rebell
    -1.92
     Quit
    -1.86
     loser
    -1.84
     disgruntled
    -1.80
     absentee
    -1.78
    sorry
    -1.77
     delinquent
    -1.76
    �
    -1.76
    POSITIVE LOGITS
     utilizes
    2.95
     utilize
    2.95
     integrates
    2.87
     integrate
    2.78
     enables
    2.72
     enable
    2.68
     util
    2.65
     connects
    2.55
     utilized
    2.54
     incorporates
    2.54
    Activations Density 0.351%

    No Known Activations