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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18846
    Prev
    Next
    INDEX
    Explanations

    the word "row" in various contexts

    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
    0:0.08
    1:0.09
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.09
    8:0.06
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
     unden
    -2.75
    kw
    -2.26
    ommod
    -2.10
    manuel
    -2.06
    gil
    -2.04
     amen
    -2.01
     neigh
    -1.96
    ++++++++
    -1.94
    dict
    -1.94
     advoc
    -1.92
    POSITIVE LOGITS
     copies
    1.98
    �
    1.98
    ebook
    1.96
     behaved
    1.91
     demonstrates
    1.88
     inserts
    1.87
     unlawfully
    1.86
     proves
    1.86
     violated
    1.85
     establishes
    1.85
    Activations Density 0.000%

    No Known Activations