© 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. 10-ATT-KK
    11. 15161
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement and benefits in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.02
    3:0.04
    4:0.05
    5:0.06
    6:0.04
    7:0.07
    8:0.01
    9:0.14
    10:0.02
    11:0.43
    Negative Logits
     influ
    -2.28
    mega
    -2.28
     crus
    -2.28
    pole
    -2.26
     Conspiracy
    -2.20
    bent
    -2.12
    erent
    -2.06
     mosqu
    -2.04
    adr
    -2.04
     PART
    -1.98
    POSITIVE LOGITS
     accessibility
    3.37
     efficiency
    3.29
     hygiene
    3.13
     reliability
    3.08
     productivity
    3.06
     quality
    3.01
     usability
    3.00
     performance
    2.93
    ability
    2.87
     capabilities
    2.87
    Activations Density 0.138%

    No Known Activations