© 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. 22205
    Prev
    Next
    INDEX
    Explanations

    information related to people, particularly their attributes like name and age

    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
    0:0.07
    1:0.04
    2:0.08
    3:0.06
    4:0.28
    5:0.09
    6:0.04
    7:0.06
    8:0.07
    9:0.05
    10:0.05
    11:0.07
    Negative Logits
     raping
    -2.46
    kus
    -2.36
     sexually
    -2.34
    raped
    -2.29
     nightmares
    -2.25
     posing
    -2.25
     mascul
    -2.24
     rapist
    -2.23
     pornographic
    -2.23
     disillusion
    -2.22
    POSITIVE LOGITS
    }.
    6.40
     }
    6.38
    )}
    6.22
    }}}
    6.20
    ]}
    6.13
    }
    6.10
     },
    6.05
     {
    6.00
    },
    5.96
    };
    5.75
    Activations Density 0.046%

    No Known Activations