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. 44447
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics related to various topics

    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
    0:0.06
    1:0.01
    2:0.21
    3:0.03
    4:0.04
    5:0.04
    6:0.12
    7:0.06
    8:0.13
    9:0.04
    10:0.05
    11:0.15
    Negative Logits
    gow
    -1.86
     Citiz
    -1.73
    ako
    -1.49
    edia
    -1.39
     PUBLIC
    -1.35
    OWS
    -1.28
     dumps
    -1.28
    acco
    -1.25
    USA
    -1.25
     Dept
    -1.23
    POSITIVE LOGITS
     apiece
    1.85
     respectively
    1.68
    pound
    1.48
     alike
    1.46
     pairs
    1.45
    acters
    1.43
     pounds
    1.41
    foot
    1.40
     hybrid
    1.33
     perished
    1.33
    Activations Density 0.014%

    No Known Activations