© 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. 40153
    Prev
    Next
    INDEX
    Explanations

    names of public figures and their titles or positions

    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
    0:0.10
    1:0.02
    2:0.09
    3:0.06
    4:0.28
    5:0.02
    6:0.02
    7:0.03
    8:0.14
    9:0.06
    10:0.07
    11:0.06
    Negative Logits
     })
    -1.63
     violates
    -1.57
     },
    -1.56
     constitutes
    -1.54
    phas
    -1.49
     inheritance
    -1.49
     exceeds
    -1.48
     emits
    -1.43
     });
    -1.41
     entails
    -1.41
    POSITIVE LOGITS
     Cree
    1.59
    dinand
    1.58
    ALSE
    1.57
     Cha
    1.55
    icio
    1.50
     Lia
    1.40
     competitor
    1.39
    irlf
    1.38
    enda
    1.36
     Hath
    1.35
    Activations Density 0.153%

    No Known Activations