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. 3-ATT-KK
    6. 8364
    Prev
    Next
    INDEX
    Explanations

    references to switches and their operation or connection in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.02
    2:0.05
    3:0.11
    4:0.02
    5:0.03
    6:0.11
    7:0.30
    8:0.05
    9:0.04
    10:0.06
    11:0.11
    Negative Logits
     childbirth
    -1.09
     Uriel
    -1.06
     VICE
    -1.04
     Enough
    -1.03
     firsthand
    -1.00
    llah
    -0.97
    Narr
    -0.95
     Guinness
    -0.94
     Arbor
    -0.94
     UNESCO
    -0.93
    POSITIVE LOGITS
    odan
    1.24
    rero
    1.17
    ocus
    1.16
     routers
    1.13
    apters
    1.13
     actionGroup
    1.09
    ipolar
    1.08
     poles
    1.08
    hawk
    1.05
    ifix
    1.04
    Activations Density 0.012%

    No Known Activations