© 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. 9-ATT-KK
    11. 5059
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or behaviors, particularly those associated with ongoing processes or impacts

    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
    0:0.05
    1:0.03
    2:0.07
    3:0.03
    4:0.07
    5:0.03
    6:0.28
    7:0.04
    8:0.08
    9:0.20
    10:0.02
    11:0.04
    Negative Logits
    ollah
    -3.82
    aito
    -3.82
    alore
    -3.79
    ajor
    -3.72
     DI
    -3.54
     divest
    -3.46
    atti
    -3.30
    endon
    -3.29
    illo
    -3.27
     Deg
    -3.26
    POSITIVE LOGITS
     Snow
    11.56
    Snow
    11.50
     snow
    9.12
     snowy
    6.87
     Winter
    5.76
     Ice
    5.76
     skiing
    5.66
     Frost
    5.58
     Glacier
    5.58
    Winter
    5.46
    Activations Density 0.010%

    No Known Activations