© 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. 2-ATT-KK
    6. 21467
    Prev
    Next
    INDEX
    Explanations

    references to specific quantities or pieces of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.23
    3:0.04
    4:0.27
    5:0.04
    6:0.02
    7:0.02
    8:0.04
    9:0.14
    10:0.04
    11:0.02
    Negative Logits
     Sloan
    -1.47
    STD
    -1.43
     Enhancement
    -1.35
    �
    -1.23
    WOR
    -1.21
     outweigh
    -1.20
    ayn
    -1.19
     steroid
    -1.17
    YN
    -1.17
    aq
    -1.17
    POSITIVE LOGITS
    selage
    1.43
     mortar
    1.36
     precincts
    1.33
    ensis
    1.33
    actory
    1.30
    loe
    1.28
    yang
    1.26
     humour
    1.25
     decoration
    1.24
    ateral
    1.24
    Activations Density 0.005%

    No Known Activations