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. 7129
    Prev
    Next
    INDEX
    Explanations

    mentions of risks or dangers related to investments or business operations

    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
    0:0.10
    1:0.05
    2:0.19
    3:0.10
    4:0.07
    5:0.08
    6:0.08
    7:0.03
    8:0.07
    9:0.08
    10:0.07
    11:0.04
    Negative Logits
     orchestr
    -1.60
     sacrific
    -1.49
     lev
    -1.41
     Leban
    -1.36
     sparing
    -1.36
    geries
    -1.36
    iltr
    -1.35
     intermitt
    -1.33
     volunte
    -1.33
     accomp
    -1.32
    POSITIVE LOGITS
    was
    1.59
    ought
    1.57
    said
    1.56
     ain
    1.56
    quickShipAvailable
    1.53
     denies
    1.47
    inventoryQuantity
    1.46
    Bay
    1.45
    will
    1.42
    FK
    1.41
    Activations Density 0.022%

    No Known Activations