© 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. 1524
    Prev
    Next
    INDEX
    Explanations

    numeric data related to pH levels and substances affecting acidity

    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
    0:0.25
    1:0.02
    2:0.13
    3:0.08
    4:0.04
    5:0.10
    6:0.05
    7:0.04
    8:0.10
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
     carriage
    -3.09
    Fal
    -2.80
    LM
    -2.73
    ulia
    -2.65
    ascar
    -2.57
    fif
    -2.41
     Fors
    -2.39
     CIS
    -2.38
    glas
    -2.37
     Airbus
    -2.30
    POSITIVE LOGITS
     pH
    5.62
     acidic
    4.48
     Acid
    3.81
     acid
    3.59
    acid
    3.40
     alk
    3.40
     Jelly
    3.15
     Tap
    3.00
     acids
    2.85
     Pond
    2.83
    Activations Density 0.002%

    No Known Activations