© 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. 9-ATT-KK
    11. 20591
    Prev
    Next
    INDEX
    Explanations

    references to news and journalism

    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
    0:0.16
    1:0.01
    2:0.17
    3:0.12
    4:0.05
    5:0.11
    6:0.05
    7:0.09
    8:0.08
    9:0.01
    10:0.08
    11:0.02
    Negative Logits
     aest
    -1.97
    rarily
    -1.95
     comparisons
    -1.89
     residues
    -1.86
     oranges
    -1.76
    mittedly
    -1.76
     dexter
    -1.74
     resorted
    -1.73
     disliked
    -1.73
     interchange
    -1.71
    POSITIVE LOGITS
    Alert
    2.54
     SIGN
    2.43
     alerts
    2.39
     alert
    2.28
     notification
    2.13
     Alert
    2.11
     Password
    2.00
     wired
    2.00
     Pocket
    1.95
    @#&
    1.94
    Activations Density 0.001%

    No Known Activations