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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44439
    Prev
    Next
    INDEX
    Explanations

    references to various data and content metrics from the Internet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.03
    2:0.12
    3:0.14
    4:0.20
    5:0.03
    6:0.04
    7:0.06
    8:0.04
    9:0.04
    10:0.13
    11:0.09
    Negative Logits
    objects
    -1.89
    76561
    -1.84
     partying
    -1.67
    adra
    -1.67
    versions
    -1.64
     positions
    -1.63
    �
    -1.57
    status
    -1.52
     garments
    -1.51
    ヘ
    -1.51
    POSITIVE LOGITS
     Review
    1.78
    review
    1.65
     review
    1.64
    Review
    1.61
     Examiner
    1.61
     Crit
    1.59
    pour
    1.59
     reviewed
    1.58
     Norton
    1.58
     Insight
    1.58
    Activations Density 0.000%

    No Known Activations