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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 7900
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various aspects of intelligence and social behavior

    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
    1:0.04
    2:0.05
    3:0.28
    4:0.02
    5:0.09
    6:0.03
    7:0.05
    8:0.03
    9:0.02
    10:0.25
    11:0.03
    Negative Logits
    ceivable
    -2.33
     risked
    -2.25
    fax
    -2.10
    Shield
    -2.06
    Statement
    -1.99
    ケ
    -1.99
     hotline
    -1.99
    munition
    -1.92
    emption
    -1.91
    eday
    -1.90
    POSITIVE LOGITS
     tends
    2.89
     comed
    2.80
     slower
    2.58
     regress
    2.56
     inconsist
    2.55
     excessively
    2.52
     skewed
    2.48
     shallow
    2.48
     exagger
    2.46
     stereotyp
    2.45
    Activations Density 0.048%

    No Known Activations