© 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. 10-ATT-KK
    11. 8848
    Prev
    Next
    INDEX
    Explanations

    mentions and comparisons of mobile phone brands, specifically Android and iPhone

    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
    0:0.11
    1:0.22
    2:0.04
    3:0.04
    4:0.04
    5:0.03
    6:0.11
    7:0.09
    8:0.02
    9:0.03
    10:0.17
    11:0.06
    Negative Logits
    ��
    -3.63
     Mord
    -2.87
     calcium
    -2.82
    actionDate
    -2.76
     mosqu
    -2.72
    ��
    -2.68
     Ard
    -2.60
     nond
    -2.59
     Kov
    -2.58
     Tsuk
    -2.56
    POSITIVE LOGITS
     Fan
    7.93
    Fan
    7.14
    fan
    6.40
     fan
    5.31
     Fans
    3.98
     fandom
    3.89
     Fang
    3.56
     fanatic
    3.50
     Fre
    3.44
     Mane
    3.39
    Activations Density 0.008%

    No Known Activations