Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10443
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to political criticism and controversial figures

    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
    1:0.17
    2:0.19
    3:0.05
    4:0.02
    5:0.04
    6:0.09
    7:0.07
    8:0.12
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
     *)
    -1.36
    …)
    -1.28
     Maid
    -1.12
     recess
    -1.09
     KL
    -1.06
    .)
    -1.06
     Oval
    -1.04
     Canter
    -1.04
     loc
    -1.03
     Martial
    -1.03
    POSITIVE LOGITS
    ullivan
    1.59
    arity
    1.45
     guiName
    1.43
    aunders
    1.40
    theless
    1.35
    etheless
    1.35
    qqa
    1.30
    xtap
    1.22
    Led
    1.21
    gyn
    1.17
    Activations Density 0.103%

    No Known Activations