© 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. 43877
    Prev
    Next
    INDEX
    Explanations

    phrases or references to competitive sports and their impact on individuals

    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
    0:0.01
    1:0.01
    2:0.12
    3:0.35
    4:0.10
    5:0.05
    6:0.02
    7:0.04
    8:0.07
    9:0.08
    10:0.07
    11:0.04
    Negative Logits
    )?
    -1.90
    pires
    -1.85
    "?
    -1.80
    ocaust
    -1.77
    ?".
    -1.74
    chwitz
    -1.69
     =================================
    -1.57
    Reviewer
    -1.56
    uncture
    -1.55
    oğan
    -1.55
    POSITIVE LOGITS
     yesterday
    1.67
     NT
    1.65
     Ples
    1.51
     waivers
    1.41
     Higgins
    1.33
     intending
    1.32
     RH
    1.29
     Brach
    1.28
     Hyundai
    1.28
     whilst
    1.28
    Activations Density 1.161%

    No Known Activations