© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28238
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and phrases used to indicate lists or series of items

    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
    0:0.02
    1:0.02
    2:0.13
    3:0.12
    4:0.15
    5:0.04
    6:0.03
    7:0.06
    8:0.06
    9:0.07
    10:0.10
    11:0.13
    Negative Logits
    hyde
    -1.49
    veland
    -1.43
    nai
    -1.41
    arre
    -1.33
    vind
    -1.33
    ibal
    -1.30
    emale
    -1.29
    andre
    -1.28
    ajor
    -1.27
    aila
    -1.27
    POSITIVE LOGITS
     then
    1.42
     Trails
    1.23
     Tomorrow
    1.22
     check
    1.21
     Origin
    1.21
     weeds
    1.19
     Profile
    1.18
     Puzzle
    1.16
     Topic
    1.16
     Next
    1.14
    Activations Density 0.035%

    No Known Activations