© 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. 3-ATT-KK
    11. 13499
    Prev
    Next
    INDEX
    Explanations

    names or words related to a specific person or place, potentially related to politics or law

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to specific names or entities in the context of socio-political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.05
    2:0.07
    3:0.26
    4:0.02
    5:0.02
    6:0.12
    7:0.08
    8:0.05
    9:0.12
    10:0.07
    11:0.07
    Negative Logits
     Rept
    -1.28
    ruary
    -1.23
     Samoa
    -1.14
    abase
    -1.13
     slightest
    -1.06
     necessities
    -0.95
     unequ
    -0.95
     scient
    -0.95
     rept
    -0.94
     stature
    -0.93
    POSITIVE LOGITS
    vati
    1.43
    kov
    1.37
    othal
    1.36
    eta
    1.35
    nikov
    1.33
    oj
    1.30
    pta
    1.27
    jit
    1.25
    kaya
    1.20
    agus
    1.18
    Activations Density 0.003%

    No Known Activations