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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22376
    Prev
    Next
    INDEX
    Explanations

    phrases related to implementing stricter measures or regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases associated with tightening control or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.13
    3:0.11
    4:0.08
    5:0.05
    6:0.02
    7:0.03
    8:0.18
    9:0.14
    10:0.06
    11:0.04
    Negative Logits
    Pal
    -1.15
    JECT
    -1.11
    Card
    -1.11
     Yao
    -1.08
     pige
    -1.07
    Pod
    -1.05
     cooks
    -1.03
     sacrificed
    -1.02
    podcast
    -1.02
    weet
    -1.01
    POSITIVE LOGITS
    ーテ
    1.54
    nings
    1.39
    versions
    1.28
    irements
    1.24
    notations
    1.23
     foothold
    1.22
    龍契士
    1.21
    req
    1.21
    urities
    1.20
     grip
    1.19
    Activations Density 0.008%

    No Known Activations