© 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. 10-ATT-KK
    11. 7144
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.09
    2:0.05
    3:0.20
    4:0.08
    5:0.03
    6:0.11
    7:0.16
    8:0.03
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
     Lifetime
    -2.79
     McN
    -2.51
     explo
    -2.23
     Obj
    -2.10
     ARTICLE
    -2.05
     Objective
    -2.00
     crooked
    -2.00
     Current
    -1.98
     Caption
    -1.90
    uming
    -1.89
    POSITIVE LOGITS
     arrival
    4.26
     arrive
    4.04
     arrives
    3.57
     arrived
    3.48
     arriving
    3.37
     arrivals
    3.23
     Arri
    2.30
     departure
    2.30
     disembark
    2.28
    ursday
    2.15
    Activations Density 0.005%

    No Known Activations