© 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. 3162
    Prev
    Next
    INDEX
    Explanations

    elements describing intense emotions or experiences of discomfort and reflection

    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
    0:0.07
    1:0.01
    2:0.11
    3:0.11
    4:0.06
    5:0.07
    6:0.02
    7:0.05
    8:0.07
    9:0.11
    10:0.15
    11:0.12
    Negative Logits
    ploma
    -1.15
     Founding
    -1.14
    �
    -1.11
     Lynn
    -1.09
     waivers
    -1.09
    irements
    -1.08
     criteria
    -1.07
    ategy
    -1.05
     eligibility
    -1.03
     concess
    -1.03
    POSITIVE LOGITS
     beck
    1.56
     throb
    1.49
     trickle
    1.46
     faint
    1.45
     trem
    1.39
     faintly
    1.39
     reverber
    1.38
     shimmer
    1.36
     murm
    1.31
     gaping
    1.31
    Activations Density 0.674%

    No Known Activations