© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14830
    Prev
    Next
    INDEX
    Explanations

    specific person's names and titles or mentions related to notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.34
    2:0.02
    3:0.04
    4:0.02
    5:0.01
    6:0.08
    7:0.07
    8:0.02
    9:0.02
    10:0.11
    11:0.04
    Negative Logits
     alt
    -3.41
     Takeru
    -3.18
     Chic
    -3.16
    Alt
    -3.03
     homophobic
    -2.96
    alt
    -2.93
     Pole
    -2.92
     Coch
    -2.74
     Gay
    -2.71
     firewall
    -2.69
    POSITIVE LOGITS
    ren
    6.11
    gren
    4.68
     Bren
    3.99
     Fren
    3.92
     Gren
    3.90
     gren
    3.67
    Ren
    3.54
     Hes
    3.25
     Ren
    3.12
    eren
    2.99
    Activations Density 0.001%

    No Known Activations