© 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. 10424
    Prev
    Next
    INDEX
    Explanations

    the presence of specific keywords and phrases related to themes of community, support, and functionality in various contexts

    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
    2:0.05
    3:0.05
    4:0.03
    5:0.03
    6:0.34
    7:0.02
    8:0.05
    9:0.24
    10:0.02
    11:0.02
    Negative Logits
     Sanford
    -3.78
    Maria
    -3.56
     SAP
    -3.53
     �
    -3.47
    Parameter
    -3.24
     Scala
    -3.20
     Santiago
    -3.20
     FA
    -3.18
     Maria
    -3.15
     Faul
    -3.09
    POSITIVE LOGITS
     Wheel
    9.96
     wheel
    9.00
    Wheel
    8.91
     wheels
    7.81
    wheel
    7.56
     Wheels
    7.43
    whe
    5.24
    Whe
    5.05
     axle
    4.65
     Wheeler
    4.43
    Activations Density 0.004%

    No Known Activations