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. 7-ATT-KK
    6. 18789
    Prev
    Next
    INDEX
    Explanations

    quantities and time-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.21
    1:0.05
    2:0.01
    3:0.16
    4:0.15
    5:0.06
    6:0.04
    7:0.04
    8:0.12
    9:0.06
    10:0.01
    11:0.02
    Negative Logits
     prominently
    -1.71
     exterior
    -1.68
    terior
    -1.68
     unresolved
    -1.67
     surface
    -1.64
     underlying
    -1.63
    SPA
    -1.60
     inclusion
    -1.59
     interchange
    -1.57
     Reserved
    -1.56
    POSITIVE LOGITS
    mort
    1.97
    mining
    1.80
    assuming
    1.75
    .–
    1.73
    eks
    1.73
    zers
    1.73
     🙂
    1.65
    loads
    1.65
    HK
    1.64
    days
    1.60
    Activations Density 0.050%

    No Known Activations