© 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. 8495
    Prev
    Next
    INDEX
    Explanations

    document structure elements, specifically identifiers or labels

    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
    2:0.09
    3:0.07
    4:0.06
    5:0.03
    6:0.08
    7:0.08
    8:0.06
    9:0.06
    10:0.08
    11:0.27
    Negative Logits
    effic
    -2.45
     surges
    -2.37
     slows
    -2.23
     downstream
    -2.18
     surging
    -2.16
     drains
    -2.14
    levels
    -2.13
     accelerating
    -2.08
    train
    -2.07
    forces
    -2.05
    POSITIVE LOGITS
     surname
    2.46
     surn
    2.17
     Arabic
    2.10
     Marriage
    1.97
     wedding
    1.97
     lamb
    1.95
    bah
    1.88
     cheek
    1.88
     notation
    1.87
    ographs
    1.86
    Activations Density 0.000%

    No Known Activations