© 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. 1413
    Prev
    Next
    INDEX
    Explanations

    references to legality and legal practices

    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
    0:0.13
    1:0.03
    2:0.25
    3:0.09
    4:0.05
    5:0.08
    6:0.06
    7:0.07
    8:0.05
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
     registrations
    -2.62
     Processing
    -2.59
     bogus
    -2.58
     targets
    -2.55
     Roundup
    -2.54
     Target
    -2.48
     target
    -2.47
     targeting
    -2.44
     Tracking
    -2.38
     targeted
    -2.36
    POSITIVE LOGITS
    闘
    2.81
     truce
    2.69
     solidarity
    2.65
     handshake
    2.58
    agall
    2.56
     cohesion
    2.48
    hesion
    2.44
     condol
    2.40
     heroism
    2.39
     pacif
    2.37
    Activations Density 0.000%

    No Known Activations