© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-ATT-KK
    11. 12689
    Prev
    Next
    INDEX
    Explanations

    references to music production techniques and DJ performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.21
    1:0.02
    2:0.10
    3:0.06
    4:0.03
    5:0.08
    6:0.07
    7:0.05
    8:0.21
    9:0.05
    10:0.03
    11:0.03
    Negative Logits
     Snyder
    -3.44
     gobl
    -3.42
     Bowen
    -3.34
    wolves
    -3.32
     Whitman
    -3.25
     orcs
    -3.24
    nyder
    -3.21
     [&
    -3.17
    renheit
    -3.17
     hikers
    -3.11
    POSITIVE LOGITS
     DJ
    8.07
     DJs
    8.06
    DJ
    7.48
     remix
    5.55
     Remix
    4.73
     Disco
    4.71
     dj
    4.23
     disco
    4.14
     MIDI
    4.13
     Dj
    4.09
    Activations Density 0.010%

    No Known Activations