© 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. 5-ATT-KK
    11. 2212
    Prev
    Next
    INDEX
    Explanations

    words associated with personal or collective responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.48
    2:0.03
    3:0.03
    4:0.02
    5:0.11
    6:0.02
    7:0.02
    8:0.04
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
    llo
    -1.84
    llers
    -1.73
    ENC
    -1.65
    rique
    -1.64
    illi
    -1.60
    riber
    -1.57
     92
    -1.54
    uti
    -1.54
    Mount
    -1.54
    56
    -1.52
    POSITIVE LOGITS
     AS
    1.99
    as
    1.93
     assum
    1.90
    ゴン
    1.89
    ascript
    1.87
    AS
    1.68
    ouls
    1.67
    mbuds
    1.67
    heid
    1.65
     Nou
    1.64
    Activations Density 0.019%

    No Known Activations