© 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. 17740
    Prev
    Next
    INDEX
    Explanations

    phrases indicating failure or unmet expectations

    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
    0:0.13
    1:0.12
    2:0.04
    3:0.06
    4:0.03
    5:0.16
    6:0.03
    7:0.02
    8:0.12
    9:0.09
    10:0.08
    11:0.06
    Negative Logits
     reaches
    -1.39
     prosec
    -1.37
     warns
    -1.35
     awaits
    -1.32
     spy
    -1.29
     VICE
    -1.29
     retrie
    -1.27
     MUST
    -1.25
     MM
    -1.22
     climbs
    -1.22
    POSITIVE LOGITS
    ��
    1.80
    pired
    1.67
     Ended
    1.62
    iliated
    1.54
    created
    1.53
     enriched
    1.51
    didn
    1.46
    unia
    1.44
    respected
    1.43
    anship
    1.43
    Activations Density 0.068%

    No Known Activations