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. 18825
    Prev
    Next
    INDEX
    Explanations

    actions related to configuration, usage, and accessibility of services or products

    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
    0:0.13
    1:0.03
    2:0.01
    3:0.10
    4:0.30
    5:0.05
    6:0.05
    7:0.03
    8:0.12
    9:0.08
    10:0.02
    11:0.02
    Negative Logits
    SPONSORED
    -2.62
     respectively
    -2.25
    uca
    -2.23
     whichever
    -2.18
    auri
    -2.12
     Parables
    -2.10
    ONEY
    -2.09
     Rebell
    -2.06
     attRot
    -2.00
     Romance
    -1.93
    POSITIVE LOGITS
    etsk
    2.01
    UGC
    1.86
    OV
    1.82
    Box
    1.81
    Includes
    1.81
     Bigfoot
    1.78
     STL
    1.78
     LB
    1.78
     wallet
    1.77
     HK
    1.76
    Activations Density 0.001%

    No Known Activations