© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 676
    Prev
    Next
    INDEX
    Explanations

    mentions of data formats, particularly JSON and XML

    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
    0:0.17
    1:0.03
    2:0.10
    3:0.05
    4:0.04
    5:0.07
    6:0.10
    7:0.06
    8:0.10
    9:0.13
    10:0.04
    11:0.05
    Negative Logits
    anqu
    -3.29
    adows
    -3.25
    perture
    -3.21
     Asus
    -3.20
     Stall
    -3.19
     Scythe
    -3.15
    Zen
    -3.04
    pac
    -3.02
     curtains
    -3.00
    asus
    -2.98
    POSITIVE LOGITS
     JSON
    7.54
    JSON
    7.18
     json
    6.00
    json
    5.76
    eson
    4.54
     parsing
    4.38
     parsed
    4.25
    Parser
    4.17
     parser
    3.99
     Pod
    3.89
    Activations Density 0.006%

    No Known Activations