© 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. 36156
    Prev
    Next
    INDEX
    Explanations

    the word "but" along with discussions of contrast or exceptions

    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
    0:0.04
    1:0.02
    2:0.11
    3:0.06
    4:0.10
    5:0.04
    6:0.03
    7:0.05
    8:0.17
    9:0.10
    10:0.07
    11:0.15
    Negative Logits
     Mehran
    -1.56
    Winner
    -1.25
    osate
    -1.25
    kef
    -1.23
    iotic
    -1.23
    WARE
    -1.23
    ERT
    -1.21
    ashtra
    -1.20
    winner
    -1.19
    quished
    -1.18
    POSITIVE LOGITS
     trains
    1.35
     nonetheless
    1.27
     peaked
    1.26
     train
    1.26
     partic
    1.21
     dunno
    1.17
     ICE
    1.16
     nevertheless
    1.15
     preferably
    1.14
     then
    1.11
    Activations Density 0.196%

    No Known Activations