© 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. 33761
    Prev
    Next
    INDEX
    Explanations

    statements asserting the presence or characteristics of specific subjects

    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
    2:0.08
    3:0.10
    4:0.08
    5:0.06
    6:0.16
    7:0.04
    8:0.03
    9:0.11
    10:0.11
    11:0.13
    Negative Logits
    aukee
    -1.44
    覚醒
    -1.26
     condem
    -1.25
    etheless
    -1.22
    \<
    -1.21
     traged
    -1.16
    ategory
    -1.14
    isconsin
    -1.13
     engagements
    -1.10
     comr
    -1.10
    POSITIVE LOGITS
     CE
    1.09
     stem
    1.07
     regress
    1.04
    urable
    1.01
     Leap
    1.00
    à
    1.00
    RP
    1.00
    ortun
    0.99
    igent
    0.99
     Phi
    0.97
    Activations Density 0.116%

    No Known Activations