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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14350
    Prev
    Next
    INDEX
    Explanations

    references to social issues, particularly those related to victimization and community welfare

    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
    0:0.03
    1:0.02
    2:0.08
    3:0.08
    4:0.10
    5:0.29
    6:0.02
    7:0.05
    8:0.02
    9:0.12
    10:0.06
    11:0.06
    Negative Logits
     positives
    -2.73
     Outlook
    -2.55
    aways
    -2.36
    JECT
    -2.35
    龍
    -2.34
    OK
    -2.30
     ahead
    -2.24
     Sho
    -2.24
    WOR
    -2.18
     Thunder
    -2.15
    POSITIVE LOGITS
     )))
    3.00
     ",
    2.98
     ));
    2.84
    ?)
    2.84
     hath
    2.78
    ?",
    2.72
     didnt
    2.71
     dunno
    2.71
     ))
    2.64
    pmwiki
    2.63
    Activations Density 0.113%

    No Known Activations