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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 27515
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences or phrases

    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
    0:0.17
    1:0.09
    2:0.06
    3:0.06
    4:0.04
    5:0.10
    6:0.02
    7:0.01
    8:0.17
    9:0.08
    10:0.03
    11:0.11
    Negative Logits
    endez
    -1.54
    luck
    -1.54
    ADRA
    -1.50
    ramid
    -1.49
    479
    -1.43
    plet
    -1.42
    munition
    -1.35
    ason
    -1.33
    lease
    -1.31
    EMBER
    -1.27
    POSITIVE LOGITS
    etc
    2.08
     etc
    1.95
     Sasha
    1.62
     Conclusion
    1.47
    OVA
    1.43
     Kyoto
    1.38
     Ibid
    1.36
     Finally
    1.32
     Iv
    1.32
     vo
    1.25
    Activations Density 0.018%

    No Known Activations