Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7752
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.08
    2:0.10
    3:0.09
    4:0.07
    5:0.08
    6:0.09
    7:0.09
    8:0.08
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
    conservancy
    -1.40
    FTWARE
    -1.34
    urga
    -1.30
    GoldMagikarp
    -1.23
     acceler
    -1.21
    byss
    -1.20
    hement
    -1.20
     awa
    -1.17
    Footnote
    -1.17
    orious
    -1.12
    POSITIVE LOGITS
    "]
    1.57
    ][
    1.50
    ]
    1.47
    ]]
    1.43
    ]-
    1.35
    ']
    1.29
    widget
    1.29
    ]=
    1.29
    ];
    1.29
    ]:
    1.26
    Activations Density 0.008%

    No Known Activations