© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 23287
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning and investigating events or individuals

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

    instances of being subjected to action or authority, often expressing themes of coercion or obligation

    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
    0:0.04
    1:0.02
    2:0.33
    3:0.04
    4:0.05
    5:0.09
    6:0.02
    7:0.02
    8:0.21
    9:0.04
    10:0.05
    11:0.02
    Negative Logits
     easing
    -1.23
     graft
    -1.22
    idency
    -1.20
    telling
    -1.18
     downs
    -1.18
    aleb
    -1.16
     harbor
    -1.14
    riz
    -1.10
    orship
    -1.10
     gotta
    -1.07
    POSITIVE LOGITS
    quished
    1.50
    ーク
    1.37
    PDATE
    1.36
     guiName
    1.35
    ット
    1.32
    ictionary
    1.32
    rozen
    1.31
    ャ
    1.27
     Wheels
    1.24
    leground
    1.24
    Activations Density 0.094%

    No Known Activations