© 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. 19322
    Prev
    Next
    INDEX
    Explanations

    advice or recommendations regarding actions and consequences

    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
    0:0.05
    1:0.03
    2:0.08
    3:0.18
    4:0.03
    5:0.06
    6:0.02
    7:0.03
    8:0.02
    9:0.02
    10:0.42
    11:0.02
    Negative Logits
    rawdownloadcloneembedreportprint
    -2.41
     sqor
    -2.29
    ulia
    -2.18
    apeshifter
    -2.05
    Untitled
    -2.02
     reveals
    -2.02
    Result
    -1.98
    igsaw
    -1.97
     attm
    -1.91
     Via
    -1.90
    POSITIVE LOGITS
     beware
    2.91
     moratorium
    2.72
     reconsider
    2.67
     caution
    2.65
     ashamed
    2.61
    ���
    2.51
     preferably
    2.47
     boycott
    2.47
    instead
    2.46
     disqual
    2.44
    Activations Density 0.249%

    No Known Activations