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. 8500
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and discussions of political unity and discipline

    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
    2:0.12
    3:0.09
    4:0.02
    5:0.03
    6:0.18
    7:0.27
    8:0.06
    9:0.03
    10:0.07
    11:0.03
    Negative Logits
    awaru
    -1.35
    アル
    -1.33
    ーティ
    -1.25
    yss
    -1.23
    igmat
    -1.20
    urnal
    -1.17
     encount
    -1.17
    GGGGGGGG
    -1.16
    achu
    -1.13
    mallow
    -1.13
    POSITIVE LOGITS
    tones
    1.46
    atives
    1.29
     Hes
    1.28
    isms
    1.26
    offs
    1.24
    ages
    1.22
    vers
    1.21
    roxy
    1.20
    notations
    1.17
    ials
    1.17
    Activations Density 0.805%

    No Known Activations