© 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. 7124
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations and advocacy groups

    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
    0:0.04
    1:0.06
    2:0.06
    3:0.02
    4:0.07
    5:0.30
    6:0.07
    7:0.06
    8:0.06
    9:0.04
    10:0.10
    11:0.06
    Negative Logits
     shocks
    -1.95
     slit
    -1.95
     hardness
    -1.94
     stroke
    -1.93
     lips
    -1.93
     kiss
    -1.92
     outburst
    -1.92
     tumble
    -1.85
     fade
    -1.82
     flashes
    -1.82
    POSITIVE LOGITS
     sponsoring
    2.33
     publishing
    2.04
    osponsors
    2.02
     publishes
    1.95
     sponsorship
    1.93
    venue
    1.92
    affiliated
    1.92
    Website
    1.90
    ourced
    1.88
     Cosponsors
    1.88
    Activations Density 0.662%

    No Known Activations