© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28562
    Prev
    Next
    INDEX
    Explanations

    terms related to sales and top-selling products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.12
    3:0.06
    4:0.12
    5:0.03
    6:0.04
    7:0.29
    8:0.02
    9:0.03
    10:0.10
    11:0.10
    Negative Logits
    ieu
    -1.44
    shadow
    -1.44
    Skip
    -1.37
    mble
    -1.35
    ymm
    -1.30
                    
    -1.27
    roots
    -1.26
    abre
    -1.24
     tang
    -1.21
    Truth
    -1.20
    POSITIVE LOGITS
    assets
    1.55
     groceries
    1.50
     newspapers
    1.50
    amazon
    1.42
     merchandise
    1.39
     licences
    1.38
    ْ
    1.38
     trophies
    1.36
     fuels
    1.36
    netflix
    1.35
    Activations Density 0.004%

    No Known Activations