© 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. 10379
    Prev
    Next
    INDEX
    Explanations

    instances of accountability and accusations within a context

    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
    0:0.09
    1:0.02
    2:0.06
    3:0.04
    4:0.04
    5:0.03
    6:0.26
    7:0.04
    8:0.09
    9:0.22
    10:0.03
    11:0.04
    Negative Logits
    bush
    -4.29
     Hitchcock
    -3.81
     Lisp
    -3.69
     Hawk
    -3.64
     Nash
    -3.61
     Lindsey
    -3.48
    razil
    -3.43
     Lyme
    -3.36
    riks
    -3.32
     Archdemon
    -3.31
    POSITIVE LOGITS
     Cu
    9.79
    Cu
    9.01
     cu
    6.73
    cu
    6.64
     Pu
    6.61
    CU
    5.60
     CU
    5.07
    Fu
    4.94
     Ku
    4.89
    uci
    4.65
    Activations Density 0.002%

    No Known Activations