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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10232
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory actions

    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
    0:0.08
    1:0.02
    2:0.08
    3:0.36
    4:0.07
    5:0.07
    6:0.02
    7:0.05
    8:0.07
    9:0.02
    10:0.09
    11:0.01
    Negative Logits
    ̶
    -2.54
    ?",
    -2.53
     stagn
    -2.43
     神
    -2.35
     stagnation
    -2.31
    shr
    -2.29
    arching
    -2.27
     longing
    -2.25
    �
    -2.25
     oppressed
    -2.23
    POSITIVE LOGITS
     affidav
    3.57
     documents
    3.25
     transcripts
    3.16
     filings
    3.13
     reports
    3.13
    reports
    3.09
     Newsweek
    3.08
     excerpts
    3.03
     spokesman
    3.01
     Politico
    2.99
    Activations Density 0.177%

    No Known Activations