© 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. 37630
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or entities associated with events or individuals

    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
    0:0.06
    1:0.11
    2:0.04
    3:0.05
    4:0.04
    5:0.20
    6:0.05
    7:0.01
    8:0.08
    9:0.21
    10:0.08
    11:0.02
    Negative Logits
    fair
    -2.04
    ONSORED
    -2.01
     mathematics
    -1.92
     stiff
    -1.92
    bread
    -1.90
     GL
    -1.83
     Hulu
    -1.82
    pless
    -1.82
     foc
    -1.80
    hops
    -1.79
    POSITIVE LOGITS
    zon
    2.81
     Hyde
    2.55
    idine
    2.52
    ゴン
    2.50
     Genocide
    2.45
    senal
    2.41
    xit
    2.36
    ��
    2.35
    ukong
    2.35
     Tsarnaev
    2.29
    Activations Density 0.167%

    No Known Activations