© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 26138
    Prev
    Next
    INDEX
    Explanations

    content related to social networking tools and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.10
    3:0.35
    4:0.12
    5:0.04
    6:0.03
    7:0.07
    8:0.04
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
    azeera
    -2.20
    usha
    -2.02
    enture
    -1.88
    20439
    -1.86
    ],"
    -1.85
    ),"
    -1.85
    ailand
    -1.82
    choes
    -1.81
    quished
    -1.81
    VERTISEMENT
    -1.79
    POSITIVE LOGITS
     ****
    1.92
     whoever
    1.70
     fucked
    1.64
     piss
    1.62
     kinda
    1.61
     Fuck
    1.57
     fuck
    1.54
     whichever
    1.54
     asses
    1.48
     hatched
    1.45
    Activations Density 0.051%

    No Known Activations