© 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. 27712
    Prev
    Next
    INDEX
    Explanations

    terms associated with fame and popularity

    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
    2:0.16
    3:0.10
    4:0.26
    5:0.02
    6:0.06
    7:0.15
    8:0.03
    9:0.04
    10:0.05
    11:0.06
    Negative Logits
    eways
    -1.70
    onde
    -1.65
    express
    -1.62
    cerpt
    -1.46
    regate
    -1.45
    ongyang
    -1.44
    oya
    -1.44
    sels
    -1.43
    eworks
    -1.40
    enda
    -1.40
    POSITIVE LOGITS
     kidding
    1.87
     affair
    1.85
     Centauri
    1.64
     owing
    1.58
     underestimate
    1.53
     grou
    1.51
    lier
    1.47
     Scandinavian
    1.44
     misunderstood
    1.40
     attracting
    1.38
    Activations Density 0.010%

    No Known Activations