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. 7-ATT-KK
    6. 9433
    Prev
    Next
    INDEX
    Explanations

    words related to leprosy and its symptoms or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.25
    2:0.04
    3:0.07
    4:0.02
    5:0.05
    6:0.09
    7:0.04
    8:0.08
    9:0.07
    10:0.13
    11:0.03
    Negative Logits
     mentors
    -2.43
     props
    -2.41
     Archangel
    -2.32
     Bungie
    -2.31
     ranger
    -2.31
     Activision
    -2.27
     Magnum
    -2.21
     Wiley
    -2.19
     routines
    -2.18
     Matrix
    -2.18
    POSITIVE LOGITS
    icter
    2.87
    philis
    2.82
     sclerosis
    2.74
    idia
    2.68
    clerosis
    2.66
    abetes
    2.64
    hemy
    2.61
    culosis
    2.55
    omaly
    2.54
    olk
    2.50
    Activations Density 0.001%

    No Known Activations