© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8260
    Prev
    Next
    INDEX
    Explanations

    elements related to music or artistic references

    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
    0:0.04
    1:0.28
    2:0.04
    3:0.15
    4:0.06
    5:0.03
    6:0.06
    7:0.10
    8:0.04
    9:0.03
    10:0.04
    11:0.07
    Negative Logits
    far
    -2.83
     abundantly
    -2.75
    ily
    -2.64
     Forth
    -2.54
     starve
    -2.45
    poor
    -2.38
    achus
    -2.37
    Far
    -2.33
     busy
    -2.26
    ceptor
    -2.25
    POSITIVE LOGITS
     Original
    6.02
    Original
    5.39
    original
    4.99
     original
    4.80
     originals
    4.77
     ORIG
    4.61
     Orig
    4.20
    �士
    3.57
    Orig
    3.55
     orig
    2.86
    Activations Density 0.016%

    No Known Activations