© 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. 10-ATT-KK
    11. 10573
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need for citations or references in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.05
    2:0.05
    3:0.11
    4:0.07
    5:0.31
    6:0.03
    7:0.04
    8:0.03
    9:0.15
    10:0.04
    11:0.03
    Negative Logits
     ));
    -2.89
     Anyway
    -2.68
    acebook
    -2.59
     Apart
    -2.58
     Imag
    -2.48
     Were
    -2.44
    milo
    -2.40
     Spice
    -2.39
     )))
    -2.35
    aneers
    -2.35
    POSITIVE LOGITS
    :]
    4.64
    ]'
    4.31
    ]"
    4.28
    ...]
    3.91
    .]
    3.71
    ]
    3.68
    …]
    3.59
    ]."
    3.49
    ];
    3.31
    ][
    3.25
    Activations Density 0.002%

    No Known Activations