© 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. 44866
    Prev
    Next
    INDEX
    Explanations

    the concept of seeking safety or protection

    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
    2:0.06
    3:0.05
    4:0.08
    5:0.02
    6:0.03
    7:0.44
    8:0.02
    9:0.03
    10:0.09
    11:0.09
    Negative Logits
     describ
    -1.70
     ende
    -1.53
     favorably
    -1.49
    designed
    -1.43
     descriptive
    -1.43
     positively
    -1.42
     shaping
    -1.41
    phabet
    -1.38
     promoted
    -1.36
    authored
    -1.36
    POSITIVE LOGITS
     Mouse
    1.52
     reptiles
    1.48
    Flo
    1.45
     Bed
    1.40
    uggle
    1.36
    hang
    1.35
     Thieves
    1.34
    Sleep
    1.34
     Mosque
    1.30
    ptin
    1.30
    Activations Density 0.005%

    No Known Activations