© 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. 7117
    Prev
    Next
    INDEX
    Explanations

    references to social issues and community involvement

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.04
    4:0.04
    5:0.53
    6:0.02
    7:0.03
    8:0.02
    9:0.13
    10:0.01
    11:0.03
    Negative Logits
     unsurprisingly
    -2.77
     Too
    -2.76
     hardly
    -2.68
    np
    -2.67
    itbart
    -2.62
     nowhere
    -2.59
     neither
    -2.58
     meanwhile
    -2.58
    arted
    -2.55
    Too
    -2.54
    POSITIVE LOGITS
     once
    3.93
     anymore
    3.83
     insofar
    3.56
     if
    3.09
    onse
    2.94
     when
    2.88
    when
    2.85
    rio
    2.77
     able
    2.69
    ety
    2.56
    Activations Density 0.300%

    No Known Activations