© 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. 3-ATT-KK
    11. 6396
    Prev
    Next
    INDEX
    Explanations

    strong emotional expressions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.14
    1:0.08
    2:0.07
    3:0.04
    4:0.05
    5:0.13
    6:0.06
    7:0.09
    8:0.15
    9:0.02
    10:0.08
    11:0.03
    Negative Logits
     cryptoc
    -1.52
    catentry
    -1.51
     Oval
    -1.47
    ュ
    -1.45
    ビ
    -1.42
    ppers
    -1.39
    ドラ
    -1.34
     bund
    -1.30
    =~=~
    -1.29
     crates
    -1.27
    POSITIVE LOGITS
    answer
    1.50
    icip
    1.41
     submitted
    1.39
     founded
    1.37
     reasoned
    1.35
    defined
    1.34
     answered
    1.32
     conceived
    1.31
     Discrimination
    1.29
    comment
    1.27
    Activations Density 0.123%

    No Known Activations