© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 21637
    Prev
    Next
    INDEX
    Explanations

    emphasis on feelings and subjective experiences

    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
    0:0.08
    1:0.15
    2:0.05
    3:0.05
    4:0.05
    5:0.04
    6:0.16
    7:0.05
    8:0.03
    9:0.21
    10:0.05
    11:0.04
    Negative Logits
     Kare
    -3.10
     Whe
    -2.91
     Logan
    -2.90
     Gat
    -2.86
     Magicka
    -2.75
    checks
    -2.70
    FINE
    -2.69
     Yel
    -2.66
    ovy
    -2.62
     Geral
    -2.62
    POSITIVE LOGITS
     difficult
    3.46
     Titan
    3.02
    ▬
    2.90
     transc
    2.81
     electrode
    2.77
     difficulties
    2.72
     complexities
    2.70
     tumultuous
    2.66
     opaque
    2.65
     impossibility
    2.65
    Activations Density 0.001%

    No Known Activations