© 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. 20830
    Prev
    Next
    INDEX
    Explanations

    URLs and links to online resources

    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
    0:0.16
    1:0.25
    2:0.06
    3:0.04
    4:0.03
    5:0.13
    6:0.03
    7:0.04
    8:0.04
    9:0.07
    10:0.04
    11:0.06
    Negative Logits
    tackle
    -1.78
    lins
    -1.73
    indal
    -1.71
    alone
    -1.70
     GOODMAN
    -1.68
    inth
    -1.68
    lass
    -1.67
    ogether
    -1.62
    agos
    -1.62
    luck
    -1.57
    POSITIVE LOGITS
    /
    2.31
    /_
    1.82
    /-
    1.79
    /​
    1.74
     /
    1.58
    /(
    1.58
    /?
    1.56
    /)
    1.53
    ・
    1.51
     Juda
    1.51
    Activations Density 0.004%

    No Known Activations