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. 7246
    Prev
    Next
    INDEX
    Explanations

    references related to student loans and financial struggles

    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
    0:0.01
    1:0.01
    2:0.31
    3:0.09
    4:0.13
    5:0.02
    6:0.04
    7:0.09
    8:0.05
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     parentheses
    -1.75
     placeholder
    -1.49
     enclosed
    -1.44
    paren
    -1.44
     ceiling
    -1.39
    dated
    -1.37
     reserved
    -1.37
     pecul
    -1.35
     Voyager
    -1.35
     Duration
    -1.34
    POSITIVE LOGITS
    aughs
    1.61
    IENCE
    1.60
    hirt
    1.57
    conom
    1.56
     improve
    1.56
    gow
    1.53
    uckles
    1.51
    ugh
    1.48
    imore
    1.47
    bett
    1.47
    Activations Density 0.080%

    No Known Activations