© 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. 16686
    Prev
    Next
    INDEX
    Explanations

    elements related to social media interaction or promotional content

    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
    2:0.06
    3:0.04
    4:0.07
    5:0.03
    6:0.26
    7:0.03
    8:0.07
    9:0.22
    10:0.02
    11:0.05
    Negative Logits
     airst
    -3.87
     doll
    -3.81
     mattress
    -3.77
     motel
    -3.76
    ̶
    -3.64
     sock
    -3.59
     closet
    -3.58
     socks
    -3.49
     condom
    -3.36
    pipe
    -3.31
    POSITIVE LOGITS
    Golden
    9.25
     Golden
    9.10
     golden
    5.97
     Warriors
    5.87
    riors
    5.35
    gold
    5.08
    PG
    4.51
    Gold
    4.40
     GF
    4.17
     Pearl
    4.07
    Activations Density 0.005%

    No Known Activations