© 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. 20598
    Prev
    Next
    INDEX
    Explanations

    negative or contradictory statements regarding rights, knowledge, and legal situations

    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
    2:0.07
    3:0.21
    4:0.03
    5:0.04
    6:0.02
    7:0.04
    8:0.03
    9:0.02
    10:0.36
    11:0.01
    Negative Logits
    pmwiki
    -3.07
    ertodd
    -2.34
     unfocusedRange
    -2.25
    xtap
    -2.25
    qua
    -2.23
    Pool
    -2.18
     seamlessly
    -2.17
    pez
    -2.11
     smoothly
    -2.10
    oother
    -2.09
    POSITIVE LOGITS
     doubts
    3.78
     doubt
    3.19
     concerns
    3.17
     clue
    3.12
     suspicions
    3.10
     concern
    3.09
     objection
    3.00
     nor
    2.92
     whatsoever
    2.91
     objections
    2.91
    Activations Density 0.076%

    No Known Activations