© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22040
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.17
    3:0.07
    4:0.21
    5:0.05
    6:0.02
    7:0.01
    8:0.18
    9:0.10
    10:0.03
    11:0.01
    Negative Logits
    iba
    -1.36
    Catalog
    -1.28
    indle
    -1.28
     arteries
    -1.19
     tunnels
    -1.16
    idon
    -1.16
     Mous
    -1.15
    wid
    -1.15
    margin
    -1.15
     lineback
    -1.13
    POSITIVE LOGITS
     context
    1.63
    ertodd
    1.50
     airs
    1.44
     karma
    1.28
     surname
    1.25
     suffice
    1.24
    entials
    1.24
     circumstance
    1.23
    shire
    1.22
     occasion
    1.20
    Activations Density 0.026%

    No Known Activations