© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 23173
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or religious contexts

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

    references to specific individuals and their roles or actions

    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
    0:0.15
    1:0.03
    2:0.13
    3:0.10
    4:0.06
    5:0.09
    6:0.04
    7:0.02
    8:0.08
    9:0.12
    10:0.08
    11:0.05
    Negative Logits
    ilater
    -1.22
     alike
    -1.09
    ixir
    -1.07
    IFIED
    -1.05
     wiser
    -1.05
     sight
    -1.03
     predictor
    -1.02
    sembly
    -1.02
    Published
    -1.01
    arthed
    -0.99
    POSITIVE LOGITS
    yan
    1.35
    unic
    1.24
    acs
    1.20
     Creep
    1.18
    toe
    1.16
    ols
    1.13
    kun
    1.11
    reg
    1.11
    zb
    1.11
    chens
    1.10
    Activations Density 0.031%

    No Known Activations