© 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. 27811
    Prev
    Next
    INDEX
    Explanations

    names of individuals or characters

    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
    0:0.04
    1:0.05
    2:0.02
    3:0.03
    4:0.03
    5:0.37
    6:0.02
    7:0.01
    8:0.04
    9:0.12
    10:0.14
    11:0.05
    Negative Logits
    ��
    -1.77
     cens
    -1.59
     banning
    -1.53
     accredited
    -1.52
    CVE
    -1.48
     SPECIAL
    -1.47
     NYT
    -1.44
     inaccur
    -1.39
     forecasting
    -1.35
    aution
    -1.35
    POSITIVE LOGITS
    Kyle
    1.67
    lar
    1.65
    essa
    1.64
    [[
    1.64
     Samson
    1.64
     Ler
    1.60
    rider
    1.60
    sie
    1.59
    username
    1.56
    sylv
    1.55
    Activations Density 0.169%

    No Known Activations