© 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. 3-ATT-KK
    11. 10717
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate reports, statements, or actions taken on behalf of organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.11
    3:0.32
    4:0.01
    5:0.02
    6:0.05
    7:0.08
    8:0.06
    9:0.11
    10:0.05
    11:0.10
    Negative Logits
    onics
    -1.37
    igmatic
    -1.37
    peat
    -1.27
    iston
    -1.22
    otide
    -1.20
    rimp
    -1.19
    opter
    -1.18
    uscript
    -1.17
    ulhu
    -1.15
    aeus
    -1.14
    POSITIVE LOGITS
     behalf
    1.72
     others
    1.19
     Whole
    1.17
     Lara
    1.09
     UNITED
    1.07
     Customers
    1.07
     Judge
    1.06
     Client
    1.06
     Administ
    1.06
     representations
    1.04
    Activations Density 0.005%

    No Known Activations