© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 12716
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of agents and their associated activities or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.07
    3:0.07
    4:0.05
    5:0.05
    6:0.13
    7:0.04
    8:0.05
    9:0.31
    10:0.04
    11:0.02
    Negative Logits
    Pope
    -3.67
     Cly
    -3.56
     Monkey
    -3.53
    ipple
    -3.42
    �
    -3.27
    udd
    -3.26
    ��
    -3.24
    ocy
    -3.23
    cycle
    -3.21
     lyn
    -3.21
    POSITIVE LOGITS
    Agent
    8.02
     agent
    7.94
     agents
    7.75
     Agent
    7.60
    agents
    7.54
    agent
    7.52
     Agents
    7.43
     ATF
    4.69
     Agency
    4.49
     AG
    4.40
    Activations Density 0.007%

    No Known Activations