© 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. 35331
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss distinctions and comparisons between concepts or entities

    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
    2:0.11
    3:0.09
    4:0.08
    5:0.05
    6:0.03
    7:0.21
    8:0.09
    9:0.04
    10:0.06
    11:0.15
    Negative Logits
     timer
    -1.36
    jad
    -1.24
    mail
    -1.22
    iard
    -1.19
    rice
    -1.15
     resisted
    -1.13
    ayan
    -1.13
    iant
    -1.12
    arie
    -1.11
    mount
    -1.11
    POSITIVE LOGITS
    tsky
    1.34
    lucent
    1.32
    igslist
    1.31
    erness
    1.30
    isphere
    1.29
     Night
    1.27
    asis
    1.26
    ufact
    1.25
    rawler
    1.25
     realities
    1.22
    Activations Density 0.028%

    No Known Activations