© 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. 13133
    Prev
    Next
    INDEX
    Explanations

    references to trust and its impact on various groups, particularly in social or political contexts

    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
    0:0.07
    1:0.02
    2:0.04
    3:0.14
    4:0.02
    5:0.06
    6:0.02
    7:0.05
    8:0.03
    9:0.01
    10:0.43
    11:0.05
    Negative Logits
    ーク
    -2.33
     mischief
    -2.24
    >)
    -1.96
    ptroller
    -1.95
    farious
    -1.94
    eco
    -1.90
    ��
    -1.90
    luaj
    -1.90
     explor
    -1.88
    landish
    -1.88
    POSITIVE LOGITS
     whereby
    2.80
     amongst
    2.49
     consequ
    2.37
     requiring
    2.31
     due
    2.23
     prevalent
    2.12
     residing
    2.11
     persists
    2.09
     necess
    2.08
     loyalty
    2.06
    Activations Density 0.752%

    No Known Activations