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. 2914
    Prev
    Next
    INDEX
    Explanations

    references to "man-in-the-middle" attacks and their implications in security contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.03
    2:0.22
    3:0.04
    4:0.05
    5:0.02
    6:0.16
    7:0.18
    8:0.04
    9:0.04
    10:0.06
    11:0.10
    Negative Logits
     externalToEVAOnly
    -1.49
     Gleaming
    -1.46
     condolences
    -1.46
     foster
    -1.44
     stagn
    -1.44
    龍喚士
    -1.41
     bruises
    -1.37
     mer
    -1.35
     reimburse
    -1.33
    romy
    -1.30
    POSITIVE LOGITS
    isphere
    1.64
    iHUD
    1.61
    oeuv
    1.58
    ouver
    1.58
    chuk
    1.56
    chairs
    1.56
    �士
    1.55
    etter
    1.53
    zzi
    1.53
    cking
    1.52
    Activations Density 0.001%

    No Known Activations