© 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. 10-ATT-KK
    6. 14218
    Prev
    Next
    INDEX
    Explanations

    concepts related to security and vulnerability in exchanges

    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
    0:0.13
    1:0.09
    2:0.04
    3:0.07
    4:0.03
    5:0.02
    6:0.21
    7:0.17
    8:0.01
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
    resy
    -2.61
     Alleg
    -2.42
     Wim
    -2.40
     Fritz
    -2.36
     Warn
    -2.31
     Walsh
    -2.25
    thouse
    -2.25
    Sensor
    -2.17
     Clancy
    -2.12
     pulp
    -2.12
    POSITIVE LOGITS
     exchanges
    5.98
     exchange
    5.88
     Exchange
    5.14
     exchanging
    4.24
     exch
    4.16
     exchanged
    3.93
     trading
    3.74
     traded
    3.48
     Coinbase
    3.33
     traders
    3.19
    Activations Density 0.043%

    No Known Activations