© 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. 2-ATT-KK
    11. 22567
    Prev
    Next
    INDEX
    Explanations

    numeric values related to sentences or passages in a legal or news context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to legal actions and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.01
    2:0.16
    3:0.04
    4:0.25
    5:0.04
    6:0.02
    7:0.01
    8:0.23
    9:0.07
    10:0.04
    11:0.01
    Negative Logits
    rouse
    -1.31
    ignant
    -1.30
    pir
    -1.29
    enegger
    -1.27
    PRESS
    -1.22
    ergy
    -1.16
    �
    -1.16
    QL
    -1.15
    eff
    -1.15
     Squirrel
    -1.14
    POSITIVE LOGITS
     Pastebin
    1.32
     bin
    1.28
    umbn
    1.27
    iths
    1.24
    washing
    1.23
    lain
    1.21
     mats
    1.19
    ppe
    1.16
     Bless
    1.15
    geon
    1.14
    Activations Density 0.006%

    No Known Activations