© 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. 23390
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    chemical components and their relationships in a scientific context

    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
    1:0.09
    2:0.07
    3:0.10
    4:0.05
    5:0.07
    6:0.11
    7:0.07
    8:0.07
    9:0.08
    10:0.13
    11:0.04
    Negative Logits
    ِ
    -1.48
    WN
    -1.46
    Reviewer
    -1.34
    INTER
    -1.33
    Dispatch
    -1.33
    ORPG
    -1.28
    WARE
    -1.25
    �
    -1.23
    Story
    -1.21
    VPN
    -1.19
    POSITIVE LOGITS
     purified
    1.30
     Supplement
    1.27
     Acid
    1.25
     Treatment
    1.23
     Reduced
    1.22
     lact
    1.21
     serum
    1.19
     Exposure
    1.19
     gamma
    1.19
     Prol
    1.18
    Activations Density 0.021%

    No Known Activations