© 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. 10-ATT-KK
    6. 15005
    Prev
    Next
    INDEX
    Explanations

    references to reactions and experiences regarding music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.28
    1:0.07
    2:0.07
    3:0.06
    4:0.06
    5:0.03
    6:0.07
    7:0.07
    8:0.03
    9:0.06
    10:0.05
    11:0.09
    Negative Logits
    stroke
    -3.53
     broom
    -3.12
     poker
    -3.04
     bot
    -2.98
     Vive
    -2.97
     Rabbit
    -2.94
     carrot
    -2.92
     Bot
    -2.91
     Gaw
    -2.91
     stroke
    -2.88
    POSITIVE LOGITS
     Metall
    3.73
     Album
    3.66
    Anth
    3.54
     Kendrick
    3.46
     Eminem
    3.21
     repatri
    3.05
     CDs
    3.00
    Song
    3.00
     album
    3.00
    album
    2.96
    Activations Density 0.004%

    No Known Activations