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. 3-ATT-KK
    6. 8614
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing suggestions, recommendations, or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.04
    2:0.10
    3:0.04
    4:0.02
    5:0.05
    6:0.07
    7:0.07
    8:0.05
    9:0.06
    10:0.37
    11:0.08
    Negative Logits
     necessarily
    -1.93
     anymore
    -1.87
     slightest
    -1.70
     anywhere
    -1.51
     Canaver
    -1.43
     anything
    -1.42
     Moreno
    -1.42
     bothered
    -1.40
     whatsoever
    -1.31
     mention
    -1.29
    POSITIVE LOGITS
    hai
    1.60
    wen
    1.50
    aspers
    1.41
    azel
    1.41
    ahime
    1.40
    rill
    1.32
    rek
    1.25
     SEE
    1.24
    cand
    1.24
     ancest
    1.22
    Activations Density 0.986%

    No Known Activations