© 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. 9-ATT-KK
    6. 3510
    Prev
    Next
    INDEX
    Explanations

    terms related to protection and security

    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
    0:0.04
    1:0.01
    2:0.06
    3:0.15
    4:0.02
    5:0.10
    6:0.02
    7:0.05
    8:0.02
    9:0.01
    10:0.46
    11:0.02
    Negative Logits
    acement
    -1.83
     Reconstruction
    -1.77
     mush
    -1.69
    idered
    -1.68
     blush
    -1.66
     Soccer
    -1.65
     Surgery
    -1.64
    appa
    -1.59
     sticker
    -1.58
     ribbon
    -1.54
    POSITIVE LOGITS
    against
    3.30
     against
    3.28
     Against
    2.66
     beware
    2.54
     lest
    2.50
     from
    2.49
     FROM
    2.36
     vs
    1.97
     prevents
    1.96
    Against
    1.95
    Activations Density 0.121%

    No Known Activations