© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 10029
    Prev
    Next
    INDEX
    Explanations

    specific popular hairstyles and haircuts for men

    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
    0:0.03
    1:0.05
    2:0.09
    3:0.13
    4:0.11
    5:0.06
    6:0.02
    7:0.06
    8:0.27
    9:0.06
    10:0.03
    11:0.05
    Negative Logits
     analys
    -1.92
     exhibiting
    -1.91
    withstanding
    -1.88
     GST
    -1.86
     Malays
    -1.84
     permitting
    -1.81
     captcha
    -1.81
     undertaking
    -1.75
     sickness
    -1.75
     Colonial
    -1.72
    POSITIVE LOGITS
    .
    2.53
    atography
    2.21
    jar
    2.17
    endez
    2.02
    iola
    1.99
    eno
    1.98
    LO
    1.98
    stant
    1.97
    ._
    1.96
    Ja
    1.94
    Activations Density 0.030%

    No Known Activations