© 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. 15391
    Prev
    Next
    INDEX
    Explanations

    nouns related to people or characters

    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
    0:0.17
    1:0.02
    2:0.05
    3:0.14
    4:0.06
    5:0.04
    6:0.05
    7:0.04
    8:0.10
    9:0.06
    10:0.09
    11:0.14
    Negative Logits
     vendor
    -2.64
     advantageous
    -2.61
     vendors
    -2.60
     worthless
    -2.58
     feasibility
    -2.44
     juggling
    -2.36
     disadvantage
    -2.33
     Chavez
    -2.33
     unethical
    -2.27
     bribery
    -2.26
    POSITIVE LOGITS
    �
    7.47
     �
    5.65
    †
    4.56
    �
    4.45
    »
    4.03
    ¶
    3.95
    ‎
    3.89
    �
    3.88
     ›
    3.74
     �
    3.67
    Activations Density 0.222%

    No Known Activations