© 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 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. 22216
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activity and legal issues

    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
    0:0.11
    1:0.03
    2:0.10
    3:0.03
    4:0.04
    5:0.03
    6:0.24
    7:0.05
    8:0.07
    9:0.21
    10:0.02
    11:0.03
    Negative Logits
     Buffalo
    -4.21
    Buff
    -4.04
    buff
    -3.88
     Bills
    -3.81
    leck
    -3.71
    interstitial
    -3.65
    adelphia
    -3.62
    idth
    -3.55
    Bruce
    -3.54
    urai
    -3.54
    POSITIVE LOGITS
     Sol
    9.53
    Sol
    9.24
    sol
    8.33
     sol
    8.26
     SOL
    7.28
     Solomon
    6.03
     Solitaire
    4.93
     Sole
    4.75
     solvent
    4.49
     Elastic
    4.25
    Activations Density 0.004%

    No Known Activations