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. 8633
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or decisions in political 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
    0:0.04
    1:0.05
    2:0.09
    3:0.03
    4:0.03
    5:0.12
    6:0.18
    7:0.17
    8:0.07
    9:0.03
    10:0.12
    11:0.04
    Negative Logits
    ⓘ
    -1.36
     totality
    -1.18
     versa
    -1.14
     nowhere
    -1.14
     ensl
    -1.13
     defin
    -1.12
     corrid
    -1.10
     nig
    -1.09
     contiguous
    -1.08
    NRS
    -1.08
    POSITIVE LOGITS
    kinson
    1.50
    uty
    1.50
     Jr
    1.48
    ibi
    1.34
    herty
    1.29
    redd
    1.27
     resigned
    1.26
    rompt
    1.22
    enegger
    1.21
     himself
    1.21
    Activations Density 0.218%

    No Known Activations