© 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. 10-ATT-KK
    11. 9449
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.13
    2:0.05
    3:0.06
    4:0.03
    5:0.05
    6:0.05
    7:0.08
    8:0.04
    9:0.26
    10:0.04
    11:0.14
    Negative Logits
     accelerated
    -2.53
     shortened
    -2.51
    itialized
    -2.48
     canceled
    -2.40
    Registered
    -2.35
     peaked
    -2.34
     increased
    -2.31
     decreased
    -2.29
     waning
    -2.28
     cancell
    -2.27
    POSITIVE LOGITS
    side
    3.52
     side
    3.19
     sides
    2.66
    tackle
    2.55
     Side
    2.40
    rights
    2.35
    itaire
    2.35
    onest
    2.24
     neighbor
    2.13
    eatures
    2.12
    Activations Density 0.001%

    No Known Activations