© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 35385
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or confusion in the context of bureaucratic processes

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.06
    4:0.04
    5:0.08
    6:0.05
    7:0.03
    8:0.06
    9:0.09
    10:0.39
    11:0.05
    Negative Logits
     advis
    -1.83
    grain
    -1.83
     credential
    -1.75
    hower
    -1.65
    phies
    -1.65
     pertinent
    -1.65
     geo
    -1.61
     globe
    -1.60
     achievable
    -1.59
     geop
    -1.58
    POSITIVE LOGITS
     Krish
    1.92
    letico
    1.84
    selves
    1.83
    members
    1.81
    rius
    1.77
    leaders
    1.71
    DES
    1.68
    Members
    1.65
    TRY
    1.64
    ーク
    1.64
    Activations Density 0.529%

    No Known Activations