© 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. 7013
    Prev
    Next
    INDEX
    Explanations

    phrases related to the expression and representation of opinions and views 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
    0:0.04
    1:0.01
    2:0.02
    3:0.21
    4:0.02
    5:0.25
    6:0.01
    7:0.11
    8:0.08
    9:0.01
    10:0.15
    11:0.03
    Negative Logits
    letes
    -2.02
     placeholder
    -1.99
     unknow
    -1.97
    Values
    -1.97
    =]
    -1.96
     testim
    -1.95
     000000
    -1.93
     voices
    -1.92
    Name
    -1.91
    vier
    -1.88
    POSITIVE LOGITS
     Flavoring
    2.82
    ascus
    2.64
     congestion
    2.43
    ropolis
    2.27
     Glacier
    2.20
     Traffic
    2.18
    ibaba
    2.11
     Rapid
    2.02
     Airbus
    2.01
     migration
    1.99
    Activations Density 0.010%

    No Known Activations