© 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. 8505
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to geographical and environmental conditions

    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
    0:0.07
    1:0.01
    2:0.05
    3:0.45
    4:0.03
    5:0.10
    6:0.02
    7:0.05
    8:0.05
    9:0.01
    10:0.09
    11:0.02
    Negative Logits
     successor
    -2.12
    thood
    -2.07
     involvement
    -2.04
     honorary
    -2.02
    tesy
    -1.99
     CEO
    -1.92
     predecessor
    -1.90
    Senior
    -1.81
     MVP
    -1.80
     senior
    -1.79
    POSITIVE LOGITS
     hills
    3.18
     cliffs
    3.09
     rubble
    3.07
     deserts
    2.96
     forests
    2.94
     trenches
    2.94
     streets
    2.90
     wasteland
    2.86
     mountains
    2.86
     countryside
    2.80
    Activations Density 1.008%

    No Known Activations