© 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. 9-ATT-KK
    11. 23837
    Prev
    Next
    INDEX
    Explanations

    references to popular media and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.04
    3:0.21
    4:0.03
    5:0.05
    6:0.02
    7:0.04
    8:0.03
    9:0.02
    10:0.40
    11:0.03
    Negative Logits
     distress
    -2.33
     disturbed
    -2.19
     resurg
    -2.06
     disturbance
    -2.04
     pandemonium
    -2.02
     eclips
    -2.00
     disrupted
    -1.98
     conflic
    -1.96
    affected
    -1.92
     interacted
    -1.91
    POSITIVE LOGITS
    til
    2.54
     unless
    2.40
     Pledge
    2.33
     defaults
    2.22
     clich
    2.20
     plat
    2.20
    until
    2.20
    unless
    2.19
     basics
    2.18
     until
    2.15
    Activations Density 0.018%

    No Known Activations