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. 44345
    Prev
    Next
    INDEX
    Explanations

    references to games and related content, particularly legal and procedural aspects

    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
    0:0.02
    1:0.01
    2:0.16
    3:0.13
    4:0.20
    5:0.04
    6:0.03
    7:0.10
    8:0.06
    9:0.04
    10:0.07
    11:0.09
    Negative Logits
    agonists
    -1.85
     alike
    -1.48
    esters
    -1.42
    erity
    -1.40
    ologically
    -1.37
    rists
    -1.35
     Jury
    -1.33
     palate
    -1.32
    phasis
    -1.31
     leaps
    -1.30
    POSITIVE LOGITS
     Declaration
    1.62
     expired
    1.52
    MSN
    1.50
    cdn
    1.45
    nings
    1.41
     mailing
    1.40
     files
    1.40
     Pastebin
    1.37
     file
    1.36
    eur
    1.35
    Activations Density 0.011%

    No Known Activations