© 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. 10-ATT-KK
    11. 22184
    Prev
    Next
    INDEX
    Explanations

    recognition of concepts related to marketing and business strategies

    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
    0:0.17
    1:0.16
    2:0.08
    3:0.06
    4:0.03
    5:0.01
    6:0.05
    7:0.14
    8:0.02
    9:0.03
    10:0.14
    11:0.06
    Negative Logits
     Charlottesville
    -3.00
     Sass
    -2.92
     bake
    -2.76
     batter
    -2.71
     Gillespie
    -2.69
     oxid
    -2.67
    adish
    -2.65
     hashing
    -2.60
     Khalid
    -2.56
     GPU
    -2.53
    POSITIVE LOGITS
     Tele
    7.55
     tele
    6.64
    tele
    6.28
    Tele
    6.24
     tel
    4.04
     teleport
    3.99
     teleportation
    3.97
    tel
    3.85
     Tel
    3.68
    Tel
    3.62
    Activations Density 0.005%

    No Known Activations