© 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. 9745
    Prev
    Next
    INDEX
    Explanations

    terms and classifications related to socio-economic demographics and attributes

    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
    0:0.03
    1:0.02
    2:0.44
    3:0.06
    4:0.05
    5:0.03
    6:0.04
    7:0.05
    8:0.05
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    cknowled
    -1.71
     ACTIONS
    -1.71
     PROGRAM
    -1.58
    ESSION
    -1.55
     conclud
    -1.53
     awarding
    -1.51
     IPM
    -1.50
    ETHOD
    -1.47
    olicy
    -1.46
    pkg
    -1.41
    POSITIVE LOGITS
     syndrome
    1.60
    onite
    1.59
     Doodle
    1.55
    hy
    1.46
     milk
    1.46
     Syndrome
    1.42
    itars
    1.34
     Pastebin
    1.33
    oglobin
    1.31
     Purple
    1.31
    Activations Density 0.144%

    No Known Activations