© 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. 3936
    Prev
    Next
    INDEX
    Explanations

    important societal issues and significant impacts related to events or policies

    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
    2:0.17
    3:0.11
    4:0.09
    5:0.06
    6:0.13
    7:0.10
    8:0.04
    9:0.07
    10:0.09
    11:0.04
    Negative Logits
    apons
    -2.07
    ドラ
    -1.69
    perty
    -1.66
    esthesia
    -1.65
    idium
    -1.58
    amins
    -1.57
    gdala
    -1.57
    闘
    -1.56
    ngth
    -1.55
    ��
    -1.53
    POSITIVE LOGITS
     considering
    1.58
     overdue
    1.55
     honesty
    1.53
     affair
    1.47
     indeed
    1.41
     nutshell
    1.40
     Vul
    1.39
     proposition
    1.38
     culmination
    1.37
     continuation
    1.37
    Activations Density 0.144%

    No Known Activations