© 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. 9-ATT-KK
    11. 10325
    Prev
    Next
    INDEX
    Explanations

    conditions or factors pertaining to safety and security in the use of technology or data

    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
    0:0.06
    1:0.02
    2:0.09
    3:0.26
    4:0.03
    5:0.10
    6:0.02
    7:0.08
    8:0.03
    9:0.02
    10:0.21
    11:0.02
    Negative Logits
    truth
    -2.92
    aughs
    -2.64
    facts
    -2.48
     congratulated
    -2.22
     Facts
    -2.19
     applauded
    -2.14
    justice
    -2.13
    unci
    -2.01
    answered
    -1.99
    ISTORY
    -1.97
    POSITIVE LOGITS
     chronically
    2.46
     needing
    2.45
     rainy
    2.39
     busy
    2.35
     congest
    2.17
     overcrowd
    2.17
     bothering
    2.14
     busiest
    2.14
     yourself
    2.11
     your
    2.10
    Activations Density 0.245%

    No Known Activations