© 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. 5264
    Prev
    Next
    INDEX
    Explanations

    repetition of conjunctions and articles

    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
    0:0.06
    1:0.01
    2:0.18
    3:0.08
    4:0.06
    5:0.04
    6:0.06
    7:0.03
    8:0.20
    9:0.05
    10:0.08
    11:0.11
    Negative Logits
    han
    -1.95
    yi
    -1.90
    cture
    -1.90
    *.
    -1.89
    gha
    -1.83
    rb
    -1.81
    _.
    -1.80
    Db
    -1.77
    ktop
    -1.74
    ghan
    -1.70
    POSITIVE LOGITS
    license
    1.85
     licenses
    1.72
     foregoing
    1.72
     warranties
    1.65
     lax
    1.63
     restored
    1.60
     wallets
    1.59
     compromises
    1.59
     studios
    1.56
     exclus
    1.54
    Activations Density 0.002%

    No Known Activations