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. 7-ATT-KK
    6. 9558
    Prev
    Next
    INDEX
    Explanations

    topics related to construction and regulatory processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    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
    1:0.04
    2:0.01
    3:0.10
    4:0.05
    5:0.05
    6:0.04
    7:0.02
    8:0.54
    9:0.05
    10:0.01
    11:0.01
    Negative Logits
    ヴ
    -1.61
     lash
    -1.60
     Antar
    -1.59
     lashed
    -1.58
     bearer
    -1.56
    NAS
    -1.51
     lashes
    -1.46
     declare
    -1.46
    soType
    -1.45
    llah
    -1.43
    POSITIVE LOGITS
    intensive
    2.20
     undertaken
    2.15
     underway
    2.13
     done
    2.10
     Techniques
    1.99
    method
    1.98
     intensive
    1.95
     occurring
    1.93
     facilitated
    1.92
     processes
    1.92
    Activations Density 1.260%

    No Known Activations