© 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. 9-ATT-KK
    11. 19159
    Prev
    Next
    INDEX
    Explanations

    references to sound intensity and noise levels

    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
    0:0.34
    1:0.02
    2:0.16
    3:0.10
    4:0.02
    5:0.09
    6:0.04
    7:0.05
    8:0.03
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
     redemption
    -2.62
     embryos
    -2.38
     Lann
    -2.35
     hatched
    -2.33
     Redemption
    -2.30
     Carth
    -2.29
     trustee
    -2.29
     Fitzpatrick
    -2.24
     custody
    -2.23
     Pinterest
    -2.23
    POSITIVE LOGITS
     louder
    5.52
     Audio
    5.42
     acoustic
    5.42
     audio
    5.31
     audible
    5.27
     sound
    5.26
    audio
    5.22
    Sound
    5.21
    oustic
    5.14
     noise
    5.14
    Activations Density 0.466%

    No Known Activations