© 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. 5-ATT-KK
    11. 36959
    Prev
    Next
    INDEX
    Explanations

    references to personal flaws or self-deprecating attributes in individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.18
    1:0.29
    2:0.01
    3:0.02
    4:0.01
    5:0.18
    6:0.05
    7:0.01
    8:0.12
    9:0.04
    10:0.02
    11:0.01
    Negative Logits
    MAP
    -1.90
     acron
    -1.73
    ARS
    -1.66
     FORM
    -1.64
     BUS
    -1.59
     STATS
    -1.57
    BUS
    -1.52
    MQ
    -1.48
     disrupt
    -1.47
     scram
    -1.46
    POSITIVE LOGITS
    �
    2.12
    �
    2.05
    �
    1.96
    atel
    1.95
    �
    1.94
    �
    1.94
    ��
    1.92
    �
    1.88
    els
    1.86
    �
    1.84
    Activations Density 0.123%

    No Known Activations