Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11190
    Prev
    Next
    INDEX
    Explanations

    references to the Quran

    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
    0:0.09
    1:0.07
    2:0.08
    3:0.09
    4:0.09
    5:0.06
    6:0.09
    7:0.08
    8:0.07
    9:0.08
    10:0.07
    11:0.10
    Negative Logits
    ippi
    -2.90
     Isabel
    -2.85
     Cyrus
    -2.83
     Nicol
    -2.81
     Christie
    -2.73
     Lucas
    -2.69
     Alec
    -2.67
     Brooks
    -2.66
     Sponge
    -2.65
     Burnett
    -2.64
    POSITIVE LOGITS
    】
    2.87
    gress
    2.69
     tract
    2.67
    ievers
    2.65
     Secondly
    2.64
    acea
    2.60
    uction
    2.58
    iour
    2.57
    lege
    2.54
    ortmund
    2.50
    Activations Density 0.000%

    No Known Activations