© 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. 12656
    Prev
    Next
    INDEX
    Explanations

    cooking temperatures and methods for recipes

    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
    0:0.06
    1:0.04
    2:0.05
    3:0.09
    4:0.13
    5:0.20
    6:0.02
    7:0.10
    8:0.04
    9:0.13
    10:0.04
    11:0.04
    Negative Logits
    )}
    -3.72
    )</
    -3.33
    ]}
    -3.32
     nonetheless
    -3.02
    "/>
    -2.85
     sooner
    -2.80
    ],"
    -2.79
     nevertheless
    -2.78
    }}}
    -2.77
    ":[{"
    -2.75
    POSITIVE LOGITS
     Dice
    2.21
     Chick
    2.16
     Femin
    2.12
    GGGG
    2.11
     Clare
    2.11
     Dodge
    2.08
    vag
    2.07
     Ness
    2.07
    Drop
    2.05
     Gender
    2.05
    Activations Density 0.014%

    No Known Activations