© 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. 2-ATT-KK
    11. 21315
    Prev
    Next
    INDEX
    Explanations

    references to specific online games, in this case "Neverwinter" and "Nevermind"

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.08
    1:0.03
    2:0.19
    3:0.14
    4:0.11
    5:0.07
    6:0.04
    7:0.02
    8:0.12
    9:0.07
    10:0.06
    11:0.02
    Negative Logits
    adr
    -1.34
    alyst
    -1.34
     consolidation
    -1.33
    framework
    -1.29
    tnc
    -1.22
    esm
    -1.20
    ioxide
    -1.18
    ASHINGTON
    -1.17
    processor
    -1.17
    retch
    -1.15
    POSITIVE LOGITS
     whiff
    1.38
     connects
    1.14
     Odin
    1.08
     nor
    1.06
     Nights
    1.06
     IPM
    0.99
     anywhere
    0.99
     Zan
    0.99
     Caf
    0.98
    黒
    0.98
    Activations Density 0.005%

    No Known Activations