© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 11385
    Prev
    Next
    INDEX
    Explanations

    references to NASA and its associated programs, research, and institutions

    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
    0:0.03
    1:0.05
    2:0.08
    3:0.07
    4:0.04
    5:0.04
    6:0.27
    7:0.16
    8:0.04
    9:0.04
    10:0.09
    11:0.05
    Negative Logits
     Tale
    -1.20
     Kou
    -1.11
    �
    -1.07
     Mana
    -1.05
     Disapp
    -1.03
     Shards
    -1.02
     Nek
    -1.02
     Kurd
    -1.02
    kar
    -1.02
    chan
    -1.00
    POSITIVE LOGITS
     guid
    1.29
    arthed
    1.18
    enhagen
    1.17
    tracks
    1.15
     astronauts
    1.13
    045
    1.10
    hyde
    1.09
    STD
    1.04
     inspectors
    1.03
     oversight
    1.03
    Activations Density 0.031%

    No Known Activations