© 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. 5-ATT-KK
    6. 43749
    Prev
    Next
    INDEX
    Explanations

    words related to bravery and courage, especially in challenging situations

    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
    2:0.07
    3:0.05
    4:0.08
    5:0.03
    6:0.07
    7:0.41
    8:0.03
    9:0.03
    10:0.09
    11:0.05
    Negative Logits
    NUM
    -1.72
    prints
    -1.62
    idth
    -1.55
    integer
    -1.54
     tomat
    -1.50
    HUD
    -1.48
     inscribed
    -1.48
    ciating
    -1.47
    worthiness
    -1.45
    paralle
    -1.43
    POSITIVE LOGITS
     fray
    1.90
    黒
    1.74
     Paradise
    1.67
     Chocobo
    1.65
    opard
    1.58
    aneers
    1.57
     Random
    1.56
    winter
    1.54
     Encounter
    1.54
     Survivor
    1.52
    Activations Density 0.001%

    No Known Activations