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. 3-ATT-KK
    6. 8497
    Prev
    Next
    INDEX
    Explanations

    specific brand or product names, particularly in the context of business or marketing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.11
    2:0.08
    3:0.03
    4:0.09
    5:0.05
    6:0.15
    7:0.06
    8:0.06
    9:0.06
    10:0.12
    11:0.05
    Negative Logits
    hement
    -1.82
    etheless
    -1.67
     confir
    -1.55
    ccording
    -1.47
    terness
    -1.43
     tremend
    -1.41
     SERV
    -1.40
    anwhile
    -1.34
    lihood
    -1.33
     largeDownload
    -1.27
    POSITIVE LOGITS
    Fest
    1.36
    Dad
    1.28
    Daddy
    1.19
    guard
    1.19
    Fit
    1.19
    Fix
    1.18
    Tech
    1.18
    Gear
    1.16
    tech
    1.16
     Dakota
    1.16
    Activations Density 0.680%

    No Known Activations