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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18982
    Prev
    Next
    INDEX
    Explanations

    regulatory terms and concepts related to legal and environmental standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.38
    1:0.04
    2:0.00
    3:0.05
    4:0.09
    5:0.09
    6:0.04
    7:0.02
    8:0.12
    9:0.08
    10:0.02
    11:0.02
    Negative Logits
     neglected
    -1.49
     coffers
    -1.47
     mornings
    -1.45
     tales
    -1.43
     anecdotes
    -1.42
     NEWS
    -1.41
    ...]
    -1.39
     Volks
    -1.38
     Verge
    -1.33
    orporated
    -1.33
    POSITIVE LOGITS
     allowable
    2.55
    maximum
    2.38
     maximum
    2.07
    duration
    1.97
     permissible
    1.94
    length
    1.92
    stall
    1.91
    Length
    1.89
     length
    1.88
     requirement
    1.88
    Activations Density 0.013%

    No Known Activations