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. 14515
    Prev
    Next
    INDEX
    Explanations

    phrases related to participation and engagement

    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
    0:0.03
    1:0.15
    2:0.04
    3:0.04
    4:0.07
    5:0.03
    6:0.13
    7:0.23
    8:0.04
    9:0.04
    10:0.04
    11:0.13
    Negative Logits
    Weak
    -2.47
    improve
    -2.27
     superiority
    -2.20
    �
    -2.17
    Termin
    -2.15
     overcrowd
    -2.04
     downgrade
    -2.02
     deficiency
    -2.00
    adjust
    -1.99
     Weak
    -1.97
    POSITIVE LOGITS
     involved
    2.85
     involvement
    2.61
    �
    2.41
    20439
    2.30
     pinch
    2.13
    involved
    2.09
     DPR
    2.05
     UNCLASSIFIED
    2.04
    Merit
    2.02
     mediation
    1.99
    Activations Density 0.011%

    No Known Activations