© 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. 5-ATT-KK
    6. 18668
    Prev
    Next
    INDEX
    Explanations

    information related to scientific discoveries and descriptions of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.04
    3:0.05
    4:0.03
    5:0.14
    6:0.03
    7:0.02
    8:0.13
    9:0.11
    10:0.24
    11:0.10
    Negative Logits
     democracies
    -1.44
    essions
    -1.31
    abling
    -1.29
     Greenwald
    -1.29
     nets
    -1.29
     Parties
    -1.28
     Governments
    -1.27
     majorities
    -1.27
    icial
    -1.27
     editorial
    -1.26
    POSITIVE LOGITS
    Origin
    1.65
     ooz
    1.60
    Phys
    1.58
     undergo
    1.54
    xual
    1.51
    osaurus
    1.40
     behaves
    1.36
     Specifications
    1.34
     Originally
    1.34
    ensis
    1.33
    Activations Density 0.541%

    No Known Activations