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. 3186
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to demographic and economic data

    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
    0:0.02
    1:0.09
    2:0.03
    3:0.08
    4:0.01
    5:0.09
    6:0.05
    7:0.02
    8:0.02
    9:0.36
    10:0.04
    11:0.13
    Negative Logits
    ctor
    -3.09
    creen
    -2.97
    termin
    -2.91
     Macintosh
    -2.84
    communication
    -2.75
    Wonder
    -2.74
    glas
    -2.72
    gate
    -2.66
    GC
    -2.63
    Marsh
    -2.63
    POSITIVE LOGITS
     Fei
    3.36
     Sek
    3.19
     Stats
    3.17
     Frey
    2.99
     Siren
    2.93
     VID
    2.93
     Nek
    2.92
     Fior
    2.91
    IK
    2.81
     Fit
    2.79
    Activations Density 0.031%

    No Known Activations