© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 38390
    Prev
    Next
    INDEX
    Explanations

    key phrases or significant words that signify the beginning of important events or statements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.18
    4:0.08
    5:0.05
    6:0.17
    7:0.02
    8:0.05
    9:0.11
    10:0.09
    11:0.06
    Negative Logits
    ']
    -1.58
     reused
    -1.56
    "},"
    -1.52
    Cola
    -1.52
     dece
    -1.44
     iod
    -1.43
    ]),
    -1.43
    ��
    -1.43
    ]);
    -1.43
    ],
    -1.43
    POSITIVE LOGITS
    Words
    1.58
    urrection
    1.49
    ictionary
    1.49
    hens
    1.48
    idav
    1.47
     Subtle
    1.46
     Words
    1.46
    Reviewed
    1.45
    words
    1.43
    Clar
    1.38
    Activations Density 0.062%

    No Known Activations