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. 5-ATT-KK
    6. 2943
    Prev
    Next
    INDEX
    Explanations

    questions and comments related to uncertainties and concerns in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.10
    3:0.03
    4:0.10
    5:0.03
    6:0.30
    7:0.08
    8:0.05
    9:0.04
    10:0.11
    11:0.07
    Negative Logits
    soDeliveryDate
    -1.68
    �
    -1.66
    アル
    -1.64
    ˈ
    -1.51
    エ
    -1.45
    artisan
    -1.42
    MAP
    -1.42
    ervative
    -1.38
    龍�
    -1.37
    �
    -1.33
    POSITIVE LOGITS
    rouse
    1.54
    glers
    1.48
    answered
    1.47
     answered
    1.35
    vous
    1.21
     Explain
    1.20
    comments
    1.18
     ponder
    1.17
     sus
    1.15
     hears
    1.14
    Activations Density 0.018%

    No Known Activations