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. 10-ATT-KK
    6. 14537
    Prev
    Next
    INDEX
    Explanations

    references to large, mythical marine creatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.23
    1:0.07
    2:0.10
    3:0.03
    4:0.06
    5:0.02
    6:0.06
    7:0.10
    8:0.03
    9:0.05
    10:0.15
    11:0.04
    Negative Logits
     Cadillac
    -3.60
     corrid
    -3.42
     Lynch
    -3.35
    GV
    -3.31
    rait
    -3.18
     Punjab
    -3.17
     Mercedes
    -3.02
    Lewis
    -3.02
     Quan
    -3.01
     VA
    -3.01
    POSITIVE LOGITS
     Sponge
    9.34
     Squid
    8.44
     squid
    6.16
     sponge
    5.88
    ikini
    5.46
    Squ
    4.38
     Bubble
    4.17
    onge
    4.07
     tentacles
    3.83
     jelly
    3.73
    Activations Density 0.002%

    No Known Activations