© 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. 9-ATT-KK
    11. 1955
    Prev
    Next
    INDEX
    Explanations

    references to charitable efforts and support for vulnerable populations

    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
    0:0.05
    1:0.02
    2:0.16
    3:0.18
    4:0.03
    5:0.28
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.06
    11:0.02
    Negative Logits
     negotiator
    -1.96
    onomy
    -1.89
    senal
    -1.88
    TPP
    -1.88
     oversaw
    -1.84
     outsourcing
    -1.81
    funding
    -1.80
     negoti
    -1.78
     delegated
    -1.77
     impartial
    -1.77
    POSITIVE LOGITS
     crashes
    2.09
     stricken
    2.08
     shattered
    2.01
     earthquakes
    1.95
     disturbances
    1.95
     quake
    1.93
    lost
    1.88
     torn
    1.86
     crashed
    1.85
     storms
    1.82
    Activations Density 0.657%

    No Known Activations