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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18754
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "each."

    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
    0:0.08
    1:0.07
    2:0.08
    3:0.09
    4:0.06
    5:0.07
    6:0.10
    7:0.07
    8:0.08
    9:0.10
    10:0.08
    11:0.08
    Negative Logits
    �
    -3.15
    Clock
    -3.09
    ■
    -3.06
    Tank
    -3.03
    Toy
    -2.83
    lock
    -2.76
    bull
    -2.75
    �
    -2.74
    Hall
    -2.73
     �
    -2.72
    POSITIVE LOGITS
     visas
    3.05
     psychedel
    2.99
     satellites
    2.89
     satellite
    2.86
     rever
    2.85
     visa
    2.65
     embryos
    2.61
     depreciation
    2.60
     extrater
    2.50
     prose
    2.46
    Activations Density 0.000%

    No Known Activations