© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 41617
    Prev
    Next
    INDEX
    Explanations

    attributes and formatting related to images in HTML code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.04
    1:0.02
    2:0.22
    3:0.10
    4:0.06
    5:0.02
    6:0.04
    7:0.11
    8:0.05
    9:0.04
    10:0.11
    11:0.13
    Negative Logits
    ドラゴン
    -1.43
     omission
    -1.36
    ��
    -1.27
     MIS
    -1.26
     Aberdeen
    -1.25
     Provincial
    -1.25
     misdem
    -1.23
     mend
    -1.22
     AGA
    -1.19
     Aboriginal
    -1.18
    POSITIVE LOGITS
    atten
    1.39
    .)
    1.34
    malink
    1.33
     })
    1.31
     dstg
    1.29
    ielding
    1.27
    areth
    1.24
    cheat
    1.23
    owers
    1.22
     Liberties
    1.22
    Activations Density 0.003%

    No Known Activations