© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10539
    Prev
    Next
    INDEX
    Explanations

    phrases related to inevitable change and conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.35
    1:0.04
    2:0.09
    3:0.08
    4:0.02
    5:0.06
    6:0.04
    7:0.04
    8:0.03
    9:0.05
    10:0.13
    11:0.02
    Negative Logits
    ictionary
    -2.68
     exhaustive
    -2.63
     Answers
    -2.27
    REF
    -2.26
     stren
    -2.21
    teness
    -2.19
     exhausted
    -2.10
     Frequ
    -2.09
     compuls
    -2.08
    urat
    -2.06
    POSITIVE LOGITS
    agent
    2.27
     Combine
    2.23
     brewed
    2.22
     brew
    2.21
     Cable
    2.20
     happening
    2.17
     happen
    2.13
     happens
    2.13
    agents
    2.11
     brewing
    2.09
    Activations Density 0.021%

    No Known Activations