© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 13065
    Prev
    Next
    INDEX
    Explanations

    topics related to environmental conditions and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.04
    2:0.02
    3:0.05
    4:0.07
    5:0.03
    6:0.03
    7:0.09
    8:0.01
    9:0.08
    10:0.02
    11:0.47
    Negative Logits
     Points
    -2.51
    allion
    -2.34
    Point
    -2.21
    Link
    -2.12
    Points
    -2.11
     Stat
    -2.04
    archment
    -2.03
    icus
    -2.01
    Goal
    -2.00
     Scholars
    -2.00
    POSITIVE LOGITS
     environments
    5.04
     conditions
    4.91
     environment
    4.51
     circumstances
    4.24
     climates
    4.13
     situations
    3.92
     atmosp
    3.81
     atmosphere
    3.70
     Conditions
    3.68
     surroundings
    3.54
    Activations Density 0.408%

    No Known Activations