© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14406
    Prev
    Next
    INDEX
    Explanations

    references to street-related concepts and themes

    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
    0:0.12
    1:0.14
    2:0.07
    3:0.07
    4:0.03
    5:0.02
    6:0.20
    7:0.07
    8:0.02
    9:0.04
    10:0.10
    11:0.06
    Negative Logits
     Immunity
    -2.94
     Horus
    -2.88
     Lod
    -2.81
    vae
    -2.72
     Monarch
    -2.65
     nonex
    -2.55
     Bav
    -2.53
     conserv
    -2.52
     nominating
    -2.52
     サーティワン
    -2.50
    POSITIVE LOGITS
    Street
    8.11
     Street
    7.92
    street
    7.20
     Streets
    6.89
     street
    6.86
     streets
    5.68
     streetcar
    4.71
     pavement
    4.41
     sidewalk
    4.30
     Avenue
    4.16
    Activations Density 0.052%

    No Known Activations