© 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. 9964
    Prev
    Next
    INDEX
    Explanations

    terms related to energy sources and classifications

    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
    0:0.06
    1:0.08
    2:0.06
    3:0.05
    4:0.07
    5:0.05
    6:0.21
    7:0.06
    8:0.05
    9:0.17
    10:0.03
    11:0.05
    Negative Logits
     Fog
    -3.32
     Tong
    -3.31
     Vog
    -3.21
     Noise
    -3.17
     Walsh
    -3.17
     VO
    -3.12
     Lynch
    -3.11
    Mic
    -3.09
     Mic
    -3.08
    Lyn
    -3.08
    POSITIVE LOGITS
     Secondary
    6.42
    secondary
    5.80
     secondary
    5.57
    primary
    5.19
     Primary
    4.76
    Primary
    4.72
     primary
    4.51
     tert
    4.31
     primaries
    3.84
     elementary
    3.74
    Activations Density 0.001%

    No Known Activations