© 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. 5-ATT-KK
    11. 17398
    Prev
    Next
    INDEX
    Explanations

    references to audiences and their desires or expectations

    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
    2:0.08
    3:0.06
    4:0.27
    5:0.05
    6:0.05
    7:0.17
    8:0.04
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
    anwhile
    -1.59
    eligible
    -1.58
    java
    -1.58
    culosis
    -1.56
    eport
    -1.54
     Fridays
    -1.50
     transact
    -1.43
    med
    -1.43
    SourceFile
    -1.42
     vs
    -1.41
    POSITIVE LOGITS
     sensibilities
    2.08
     Pulitzer
    1.79
     legions
    1.64
     thous
    1.63
     Gi
    1.48
     sentiments
    1.45
     buds
    1.41
     attention
    1.40
     Bram
    1.37
     heights
    1.35
    Activations Density 0.001%

    No Known Activations