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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10754
    Prev
    Next
    INDEX
    Explanations

    references to frogs and their habitats

    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
    0:0.07
    1:0.03
    2:0.06
    3:0.05
    4:0.05
    5:0.05
    6:0.22
    7:0.07
    8:0.07
    9:0.23
    10:0.02
    11:0.04
    Negative Logits
     vans
    -3.47
    hai
    -3.46
    chwitz
    -3.42
    ryn
    -3.29
    CM
    -3.27
     Ces
    -3.24
    Mich
    -3.22
     Mich
    -3.07
     Insurance
    -3.05
    obyl
    -3.05
    POSITIVE LOGITS
     Frog
    10.40
     frogs
    9.50
     frog
    9.49
    frog
    7.98
     Toad
    6.43
     trout
    5.42
     amphib
    5.38
     Pig
    4.73
     Rabbit
    4.37
     Swamp
    4.31
    Activations Density 0.000%

    No Known Activations