© 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. 10-ATT-KK
    11. 15077
    Prev
    Next
    INDEX
    Explanations

    details related to the clarification or elaboration of ideas and arguments

    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
    0:0.01
    1:0.01
    2:0.03
    3:0.48
    4:0.14
    5:0.13
    6:0.01
    7:0.02
    8:0.02
    9:0.06
    10:0.01
    11:0.02
    Negative Logits
    "],
    -4.67
    ],"
    -4.61
    ],
    -4.42
     ],
    -4.05
    ]);
    -3.98
    ]),
    -3.93
    >,
    -3.75
    ":{"
    -3.73
    ]:
    -3.52
    ];
    -3.52
    POSITIVE LOGITS
    .")
    7.83
    .)
    7.66
    .)
    7.27
    ...)
    5.91
    …)
    5.67
    !)
    5.67
    ?)
    5.12
    ,)
    4.25
     )
    4.16
    .):
    3.81
    Activations Density 0.252%

    No Known Activations