© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 7387
    Prev
    Next
    INDEX
    Explanations

    terms related to user and database operations in programming

    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
    0:0.05
    1:0.03
    2:0.04
    3:0.09
    4:0.17
    5:0.29
    6:0.03
    7:0.05
    8:0.07
    9:0.06
    10:0.03
    11:0.03
    Negative Logits
     again
    -2.75
    †
    -2.68
     exhibiting
    -2.60
     resided
    -2.54
     every
    -2.36
     anew
    -2.33
     consisting
    -2.30
     teamed
    -2.30
     intermitt
    -2.29
     totaling
    -2.29
    POSITIVE LOGITS
    });
    4.39
    },"
    4.27
    })
    4.19
     },
    4.08
    };
    4.05
    ]:
    4.03
    },
    3.97
     });
    3.91
    ':
    3.79
     })
    3.72
    Activations Density 0.015%

    No Known Activations