© 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. 3233
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "what is at stake" or "matters at the moment."

    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
    1:0.00
    2:0.15
    3:0.07
    4:0.11
    5:0.02
    6:0.07
    7:0.26
    8:0.04
    9:0.04
    10:0.06
    11:0.10
    Negative Logits
    theless
    -1.76
    ritical
    -1.70
    unker
    -1.65
    emis
    -1.49
     aux
    -1.47
    acteria
    -1.41
     paralle
    -1.41
    acco
    -1.40
    aware
    -1.40
     corps
    -1.38
    POSITIVE LOGITS
     Briggs
    1.64
     Lerner
    1.58
     Rasm
    1.55
     Heller
    1.42
    urst
    1.38
    sum
    1.35
    MRI
    1.32
     Ferr
    1.31
     Petersen
    1.30
     Judy
    1.26
    Activations Density 0.000%

    No Known Activations