© 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. 28815
    Prev
    Next
    INDEX
    Explanations

    phrases discussing knowledge and information about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.10
    3:0.04
    4:0.11
    5:0.03
    6:0.03
    7:0.27
    8:0.05
    9:0.04
    10:0.10
    11:0.14
    Negative Logits
    rive
    -1.83
    ciation
    -1.80
    river
    -1.55
    tail
    -1.51
    fired
    -1.51
     diagram
    -1.49
    ogged
    -1.45
     analogy
    -1.44
    quit
    -1.42
    tie
    -1.38
    POSITIVE LOGITS
     Extras
    1.34
    FLAG
    1.31
     Kenyan
    1.28
     Hanson
    1.25
     LGBT
    1.24
     herself
    1.24
     nutrition
    1.23
     Buddhism
    1.23
     ethnicity
    1.23
     Norn
    1.23
    Activations Density 0.005%

    No Known Activations