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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22352
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and citations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.06
    2:0.13
    3:0.09
    4:0.02
    5:0.14
    6:0.10
    7:0.08
    8:0.05
    9:0.04
    10:0.13
    11:0.07
    Negative Logits
    milo
    -1.51
    cipled
    -1.30
    EngineDebug
    -1.25
    BIP
    -1.24
    amins
    -1.24
    ierre
    -1.23
    ................................................................
    -1.22
    luaj
    -1.20
    .--
    -1.20
     (<
    -1.19
    POSITIVE LOGITS
    ].
    2.34
    ]."
    2.05
    ],
    1.93
    ]
    1.88
     ].
    1.86
    ],"
    1.78
    ]).
    1.74
    ];
    1.69
    ']
    1.69
    =]
    1.67
    Activations Density 0.023%

    No Known Activations