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. 7120
    Prev
    Next
    INDEX
    Explanations

    mentions of specific companies or brands

    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
    0:0.04
    1:0.13
    2:0.02
    3:0.03
    4:0.02
    5:0.38
    6:0.02
    7:0.01
    8:0.03
    9:0.10
    10:0.13
    11:0.03
    Negative Logits
     recess
    -1.97
     menstru
    -1.75
    irlf
    -1.61
     rite
    -1.59
     multiplication
    -1.58
     genders
    -1.58
     remem
    -1.58
    blance
    -1.58
     flashback
    -1.54
     flashbacks
    -1.54
    POSITIVE LOGITS
     Corporation
    2.22
     corporation
    2.21
    Corp
    2.21
     Industries
    2.20
     Pharma
    2.15
     Corp
    2.13
    Commerce
    2.03
    HQ
    2.00
    �
    1.96
    Company
    1.94
    Activations Density 0.180%

    No Known Activations