© 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. 20439
    Prev
    Next
    INDEX
    Explanations

    mentions of academic roles and fields of study

    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
    0:0.13
    1:0.01
    2:0.04
    3:0.21
    4:0.03
    5:0.10
    6:0.01
    7:0.04
    8:0.04
    9:0.01
    10:0.32
    11:0.02
    Negative Logits
    oks
    -2.09
     disregard
    -2.07
     impunity
    -2.01
     false
    -1.99
     refusal
    -1.96
     cheaper
    -1.89
     cheap
    -1.89
     simply
    -1.89
    false
    -1.87
     outright
    -1.86
    POSITIVE LOGITS
     studying
    2.98
     anthropology
    2.83
     neuroscience
    2.65
     researching
    2.52
     doctoral
    2.43
     sociology
    2.37
     sciences
    2.36
     Anthropology
    2.25
     studies
    2.24
     humanities
    2.16
    Activations Density 0.063%

    No Known Activations