© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 8860
    Prev
    Next
    INDEX
    Explanations

    phrases and statements regarding allegations and related comments

    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
    1:0.03
    2:0.07
    3:0.05
    4:0.05
    5:0.04
    6:0.24
    7:0.04
    8:0.06
    9:0.23
    10:0.03
    11:0.04
    Negative Logits
    Tile
    -4.41
     Sherman
    -4.24
    essee
    -3.75
     tem
    -3.72
     Templar
    -3.66
    Tes
    -3.60
    orney
    -3.53
     Confederate
    -3.44
    ilege
    -3.37
     Templ
    -3.22
    POSITIVE LOGITS
     Bang
    8.92
     Bog
    7.98
    Bang
    7.01
     Boh
    6.53
     bang
    6.18
    bang
    5.86
     Bok
    4.93
     Lug
    4.86
     Bag
    4.62
     bog
    4.50
    Activations Density 0.001%

    No Known Activations