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. 9-ATT-KK
    6. 20618
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and cooking practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.06
    3:0.12
    4:0.03
    5:0.07
    6:0.04
    7:0.42
    8:0.04
    9:0.03
    10:0.04
    11:0.02
    Negative Logits
     bye
    -2.77
     exhausted
    -2.74
     Eclipse
    -2.65
     Cinnamon
    -2.65
    ippy
    -2.58
     Estonia
    -2.56
     Eleven
    -2.52
     Wenger
    -2.46
     Wag
    -2.38
     Kuwait
    -2.38
    POSITIVE LOGITS
     interior
    2.69
    BIL
    2.52
    raint
    2.45
     [+
    2.44
     specs
    2.41
     CTR
    2.37
     CLIENT
    2.35
     shutter
    2.33
     conceal
    2.30
    tains
    2.29
    Activations Density 0.035%

    No Known Activations