© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    elements related to legal concepts and rights

    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
    0:0.04
    1:0.48
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.03
    7:0.06
    8:0.03
    9:0.04
    10:0.07
    11:0.02
    Negative Logits
    mostly
    -3.02
     rather
    -2.90
     wrongly
    -2.80
     partly
    -2.76
     latter
    -2.60
     mostly
    -2.59
    utt
    -2.50
     mainly
    -2.46
    rather
    -2.44
     chiefly
    -2.43
    POSITIVE LOGITS
     any
    6.45
     ANY
    6.04
    Any
    6.00
    any
    5.79
     Any
    5.61
     anywhere
    5.50
     anytime
    5.25
     anything
    5.19
    anything
    5.08
     anyone
    5.02
    Activations Density 0.087%

    No Known Activations