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. 18959
    Prev
    Next
    INDEX
    Explanations

    descriptions of challenges faced in various contexts

    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
    0:0.03
    1:0.06
    2:0.00
    3:0.06
    4:0.05
    5:0.40
    6:0.09
    7:0.04
    8:0.08
    9:0.08
    10:0.01
    11:0.02
    Negative Logits
    atos
    -2.68
    lez
    -2.61
    joice
    -2.44
    Happy
    -2.26
    isode
    -2.23
    mast
    -2.23
    stasy
    -2.22
    med
    -2.19
    ercise
    -2.17
    eton
    -2.15
    POSITIVE LOGITS
     unforeseen
    3.00
     creditors
    2.87
     deadlines
    2.85
     inexper
    2.74
     visa
    2.70
     constraints
    2.68
     creditor
    2.67
     jurisd
    2.56
     uncertainties
    2.55
     fractured
    2.54
    Activations Density 0.250%

    No Known Activations