© 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. 37658
    Prev
    Next
    INDEX
    Explanations

    references to identity and identification

    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
    0:0.04
    1:0.04
    2:0.08
    3:0.07
    4:0.04
    5:0.06
    6:0.38
    7:0.03
    8:0.05
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
     condem
    -1.64
     acknow
    -1.43
    wolves
    -1.42
    soever
    -1.30
     misunder
    -1.28
    essler
    -1.27
     unsus
    -1.26
    ework
    -1.26
    wagen
    -1.25
     ALWAYS
    -1.25
    POSITIVE LOGITS
    λ
    1.55
    Û
    1.51
    imil
    1.48
    hus
    1.44
    ilic
    1.39
    ω
    1.36
    gren
    1.33
    20439
    1.32
    ima
    1.31
    σ
    1.31
    Activations Density 0.004%

    No Known Activations