© 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. 5-ATT-KK
    11. 44762
    Prev
    Next
    INDEX
    Explanations

    terms related to networking and printer connectivity in office environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.01
    2:0.14
    3:0.09
    4:0.09
    5:0.06
    6:0.02
    7:0.04
    8:0.08
    9:0.08
    10:0.15
    11:0.13
    Negative Logits
     understatement
    -1.22
     underestimated
    -1.07
     underestimate
    -1.06
    onomy
    -1.04
    clerosis
    -1.01
    ourke
    -0.97
     Sophie
    -0.96
     Tory
    -0.96
    opic
    -0.95
     hindsight
    -0.94
    POSITIVE LOGITS
     contacts
    1.10
     modem
    1.07
    FTWARE
    1.06
    IRC
    1.03
     Byte
    1.03
     Arduino
    1.01
     cc
    1.00
    装
    0.97
    Plug
    0.94
    AppData
    0.93
    Activations Density 0.482%

    No Known Activations