© 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. 472
    Prev
    Next
    INDEX
    Explanations

    instances of the word "soft" in various contexts

    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
    1:0.05
    2:0.07
    3:0.05
    4:0.04
    5:0.04
    6:0.27
    7:0.06
    8:0.04
    9:0.20
    10:0.04
    11:0.04
    Negative Logits
     Corinth
    -4.06
     Cath
    -4.02
     Alban
    -3.94
     Mandal
    -3.87
    Gall
    -3.83
     itiner
    -3.76
    gall
    -3.72
     airports
    -3.68
     Barcl
    -3.65
     Apost
    -3.61
    POSITIVE LOGITS
    Soft
    7.51
     Soft
    6.87
    soft
    6.64
     soft
    6.49
     softer
    4.90
    Sw
    3.87
    Fra
    3.66
    Berry
    3.59
    opoly
    3.55
     Hardy
    3.51
    Activations Density 0.001%

    No Known Activations