© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 11068
    Prev
    Next
    INDEX
    Explanations

    assertions of claims or allegations 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
    0:0.07
    1:0.02
    2:0.04
    3:0.23
    4:0.03
    5:0.07
    6:0.02
    7:0.05
    8:0.03
    9:0.02
    10:0.36
    11:0.02
    Negative Logits
    irlf
    -1.96
    arag
    -1.94
    ocamp
    -1.89
    ummer
    -1.89
    amaru
    -1.88
    ELL
    -1.87
    trl
    -1.85
     abruptly
    -1.83
    alloween
    -1.82
     awaits
    -1.82
    POSITIVE LOGITS
     assumptions
    3.56
     convictions
    3.47
     conviction
    3.37
     assumption
    3.21
     observations
    3.02
     perceptions
    3.00
     intuition
    2.99
     premise
    2.83
     perception
    2.77
     belief
    2.77
    Activations Density 0.107%

    No Known Activations