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. 18924
    Prev
    Next
    INDEX
    Explanations

    numeric values or references to numerical data

    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
    0:0.24
    1:0.04
    2:0.03
    3:0.06
    4:0.04
    5:0.12
    6:0.07
    7:0.01
    8:0.21
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
     impat
    -1.89
     caut
    -1.80
     composure
    -1.65
     toile
    -1.61
     Vanity
    -1.61
    ealous
    -1.59
     exhaustion
    -1.58
     OCD
    -1.58
     understatement
    -1.57
     maturity
    -1.56
    POSITIVE LOGITS
    billion
    2.19
     trillion
    1.73
    asury
    1.67
    osate
    1.64
    ALT
    1.60
    nuclear
    1.56
     nuclear
    1.53
     Billion
    1.52
     uranium
    1.52
     Hasan
    1.50
    Activations Density 0.073%

    No Known Activations