Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7531
    Prev
    Next
    INDEX
    Explanations

    references to strengthening relationships and security within various contexts

    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
    0:0.03
    1:0.01
    2:0.04
    3:0.08
    4:0.15
    5:0.02
    6:0.04
    7:0.39
    8:0.04
    9:0.03
    10:0.05
    11:0.07
    Negative Logits
     Wonderland
    -1.58
    REDACTED
    -1.57
    netflix
    -1.56
    76561
    -1.52
     Firefly
    -1.47
     willingly
    -1.45
    ught
    -1.42
     QUEST
    -1.40
    龍�
    -1.37
    ��
    -1.37
    POSITIVE LOGITS
     resilience
    1.77
     defences
    1.59
     competitiveness
    1.58
    rity
    1.55
     defenses
    1.53
     foundation
    1.52
     foundations
    1.51
     Lauder
    1.50
     understanding
    1.48
     credibility
    1.45
    Activations Density 0.014%

    No Known Activations