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. 8429
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or organizational affiliations and activities

    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
    0:0.01
    1:0.02
    2:0.06
    3:0.37
    4:0.01
    5:0.02
    6:0.09
    7:0.10
    8:0.04
    9:0.09
    10:0.04
    11:0.09
    Negative Logits
    parable
    -1.52
    pard
    -1.41
    ukong
    -1.31
     foreseeable
    -1.26
    iday
    -1.26
    outed
    -1.24
    ë
    -1.24
    ewater
    -1.23
    vard
    -1.23
    ascus
    -1.22
    POSITIVE LOGITS
     Growth
    1.38
    eer
    1.38
     Ribbon
    1.31
    eers
    1.25
    aroo
    1.22
     Scrib
    1.20
     Enh
    1.17
     Ignore
    1.14
     Nationals
    1.11
     straw
    1.10
    Activations Density 0.005%

    No Known Activations