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. 130
    Prev
    Next
    INDEX
    Explanations

    references to social media platforms and online articles or content

    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
    1:0.02
    2:0.04
    3:0.13
    4:0.04
    5:0.40
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.05
    11:0.05
    Negative Logits
     publication
    -3.27
     editorial
    -2.94
    ────────
    -2.78
     publish
    -2.77
    UTC
    -2.69
     thumbnail
    -2.66
     publishes
    -2.66
     editing
    -2.58
     published
    -2.56
     editor
    -2.55
    POSITIVE LOGITS
     Flavoring
    2.30
    expensive
    2.25
    okia
    2.23
    othal
    2.20
    nesium
    2.19
     Atlantis
    2.17
    aceutical
    2.16
     Sapphire
    2.15
    erella
    2.12
    ciation
    2.11
    Activations Density 0.275%

    No Known Activations