© 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. 10-ATT-KK
    11. 14212
    Prev
    Next
    INDEX
    Explanations

    musical genres and styles

    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
    0:0.07
    1:0.04
    2:0.03
    3:0.04
    4:0.20
    5:0.03
    6:0.03
    7:0.16
    8:0.02
    9:0.05
    10:0.06
    11:0.21
    Negative Logits
     Assist
    -2.26
    ONSORED
    -2.18
    priority
    -2.18
    umbnails
    -2.17
    netflix
    -2.16
     complainant
    -2.12
    teness
    -2.11
     priority
    -2.09
    abit
    -2.05
     +++
    -2.03
    POSITIVE LOGITS
     funky
    2.62
     eclectic
    2.56
     classics
    2.50
     neo
    2.40
     Appalachian
    2.40
     esoteric
    2.35
    Americ
    2.33
     techno
    2.30
    lectic
    2.29
     Gothic
    2.29
    Activations Density 0.025%

    No Known Activations