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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19397
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the occurrence and outcomes of events, particularly those involving casualties and responses

    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
    0:0.25
    1:0.07
    2:0.09
    3:0.05
    4:0.05
    5:0.07
    6:0.06
    7:0.04
    8:0.07
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
    endment
    -1.90
    yip
    -1.79
     Allaah
    -1.63
     defe
    -1.60
    orah
    -1.57
    hof
    -1.55
    eret
    -1.52
    erous
    -1.51
    nos
    -1.50
     monopoly
    -1.50
    POSITIVE LOGITS
     Identified
    1.65
    taboola
    1.62
    ドラ
    1.56
    ceived
    1.53
     Bought
    1.52
    %).
    1.51
    gered
    1.49
     GOT
    1.49
    ivia
    1.49
    ieved
    1.48
    Activations Density 0.001%

    No Known Activations