© 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. 43695
    Prev
    Next
    INDEX
    Explanations

    the word "We" to indicate collective pronouns or references to a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.01
    2:0.06
    3:0.12
    4:0.15
    5:0.03
    6:0.13
    7:0.20
    8:0.04
    9:0.06
    10:0.04
    11:0.09
    Negative Logits
     ratios
    -1.50
     downs
    -1.46
    zers
    -1.40
    edom
    -1.36
    olesc
    -1.34
     euth
    -1.31
    wolves
    -1.28
    apo
    -1.26
    hattan
    -1.25
     Tsukuyomi
    -1.25
    POSITIVE LOGITS
    itely
    1.46
    Movie
    1.37
    Ancient
    1.29
    Record
    1.28
    aux
    1.27
    Old
    1.24
    audio
    1.23
    iverse
    1.23
    Text
    1.22
    Subscribe
    1.22
    Activations Density 0.001%

    No Known Activations