© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12941
    Prev
    Next
    INDEX
    Explanations

    difficulties associated with various challenging processes

    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
    0:0.06
    1:0.02
    2:0.07
    3:0.19
    4:0.03
    5:0.09
    6:0.01
    7:0.10
    8:0.02
    9:0.01
    10:0.32
    11:0.02
    Negative Logits
     impunity
    -2.24
    vertisement
    -2.18
    )))
    -1.88
     teasp
    -1.86
     coined
    -1.84
     endorse
    -1.83
    Tweet
    -1.81
    neutral
    -1.80
     Accessed
    -1.77
     CLSID
    -1.76
    POSITIVE LOGITS
     daunting
    3.21
     ardu
    3.04
     exhausting
    2.80
     ordeal
    2.75
     difficult
    2.67
     tedious
    2.65
     uphill
    2.65
     complicated
    2.46
     tricky
    2.43
    icult
    2.40
    Activations Density 0.759%

    No Known Activations