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. 11444
    Prev
    Next
    INDEX
    Explanations

    indications of bug fixes in software or updates

    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
    0:0.03
    1:0.30
    2:0.02
    3:0.04
    4:0.10
    5:0.03
    6:0.07
    7:0.02
    8:0.04
    9:0.09
    10:0.03
    11:0.18
    Negative Logits
     moreover
    -3.56
     theirs
    -3.35
     hers
    -3.17
     abound
    -2.99
     though
    -2.84
     ours
    -2.73
     aside
    -2.69
     aw
    -2.66
     ripe
    -2.65
     yours
    -2.64
    POSITIVE LOGITS
    Fixed
    6.43
     Fixed
    6.22
    fixed
    4.42
    Improved
    4.23
    Added
    4.12
    Removed
    4.08
     fixed
    3.89
     Updated
    3.81
     Added
    3.71
     Improved
    3.65
    Activations Density 0.003%

    No Known Activations