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. 8414
    Prev
    Next
    INDEX
    Explanations

    opinions and beliefs expressed about societal issues

    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
    1:0.06
    2:0.10
    3:0.02
    4:0.02
    5:0.04
    6:0.15
    7:0.32
    8:0.05
    9:0.04
    10:0.05
    11:0.06
    Negative Logits
    ONSORED
    -1.24
     thats
    -1.19
    terday
    -1.11
    ÍÍ
    -1.10
    Tokens
    -1.08
     Ares
    -1.05
     thous
    -1.04
    esson
    -1.03
    方
    -1.03
     congr
    -1.03
    POSITIVE LOGITS
     volunt
    1.05
    ugi
    1.01
    ibr
    1.00
    usk
    1.00
     transf
    0.99
    tu
    0.98
     neut
    0.97
     unpaid
    0.95
     themselves
    0.95
     voic
    0.95
    Activations Density 0.087%

    No Known Activations