© 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. 13396
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and health-related findings

    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
    1:0.02
    2:0.03
    3:0.04
    4:0.12
    5:0.42
    6:0.02
    7:0.04
    8:0.02
    9:0.14
    10:0.02
    11:0.04
    Negative Logits
    istries
    -3.43
    Tonight
    -3.27
    Alright
    -2.90
     wondering
    -2.81
    Disclaimer
    -2.79
     lest
    -2.75
    cair
    -2.67
     thanking
    -2.65
     Sorry
    -2.65
    Hopefully
    -2.64
    POSITIVE LOGITS
     correlate
    4.08
     significantly
    4.07
     correlates
    3.97
     correlated
    3.97
     markedly
    3.89
     decreases
    3.81
     differs
    3.78
     disproportionately
    3.76
     interacts
    3.76
     affects
    3.63
    Activations Density 0.305%

    No Known Activations