© 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. 9683
    Prev
    Next
    INDEX
    Explanations

    technical issues and problems related to software and gaming performance

    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
    1:0.02
    2:0.09
    3:0.26
    4:0.02
    5:0.15
    6:0.02
    7:0.08
    8:0.05
    9:0.02
    10:0.14
    11:0.02
    Negative Logits
     courageous
    -2.50
     educ
    -2.28
     compassionate
    -2.25
     humble
    -2.23
     courage
    -2.18
     coun
    -2.15
     philanthrop
    -2.14
     pragmatic
    -2.14
     prosperous
    -2.14
     prosperity
    -2.11
    POSITIVE LOGITS
     incorrectly
    2.97
     synchronization
    2.78
     incorrect
    2.59
     deletion
    2.57
     glitches
    2.54
     improperly
    2.54
     loading
    2.54
     errors
    2.51
     bugs
    2.50
    sync
    2.48
    Activations Density 0.808%

    No Known Activations