© 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. 20984
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant consequence or outcome

    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
    0:0.03
    1:0.05
    2:0.10
    3:0.07
    4:0.07
    5:0.04
    6:0.13
    7:0.21
    8:0.04
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
     bearer
    -1.96
     summons
    -1.71
     proposition
    -1.59
     contrary
    -1.57
     decree
    -1.56
     superiority
    -1.55
     sur
    -1.51
     supers
    -1.49
     Ribbon
    -1.47
     trump
    -1.47
    POSITIVE LOGITS
    imester
    2.21
    apeake
    2.10
    ibaba
    2.04
    yip
    2.00
    ngth
    1.99
    icago
    1.99
    lehem
    1.97
    mma
    1.95
    thodox
    1.95
    icester
    1.92
    Activations Density 0.000%

    No Known Activations