© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 12503
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory standards

    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
    0:0.06
    1:0.13
    2:0.06
    3:0.06
    4:0.04
    5:0.03
    6:0.18
    7:0.02
    8:0.03
    9:0.28
    10:0.03
    11:0.02
    Negative Logits
     Johnson
    -3.66
     Hive
    -3.62
    Johnson
    -3.42
     Kush
    -3.34
    bush
    -3.29
    eph
    -3.22
    lane
    -3.06
     visitation
    -3.01
     Polk
    -2.99
     cy
    -2.98
    POSITIVE LOGITS
     Standard
    6.64
    Standard
    6.44
     Standards
    6.15
     STAND
    6.05
     standards
    5.40
     standard
    5.34
    standard
    5.09
     standardized
    4.98
    Stand
    4.10
     SAT
    3.99
    Activations Density 0.005%

    No Known Activations