© 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. 5-ATT-KK
    11. 35953
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.07
    3:0.06
    4:0.10
    5:0.03
    6:0.05
    7:0.31
    8:0.03
    9:0.05
    10:0.10
    11:0.13
    Negative Logits
     temptation
    -1.31
     solitude
    -1.21
    OURCE
    -1.11
     Feast
    -1.11
     incentives
    -1.11
     takeaway
    -1.06
    ilitarian
    -1.06
     Gamble
    -1.06
    rawdownloadcloneembedreportprint
    -1.06
    Theme
    -1.04
    POSITIVE LOGITS
    ikers
    1.35
    devices
    1.33
     acronym
    1.25
     abbre
    1.25
    ascus
    1.23
     abbrevi
    1.22
     DOT
    1.21
    atform
    1.20
    existent
    1.15
    cule
    1.15
    Activations Density 0.002%

    No Known Activations