Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 27526
    Prev
    Next
    INDEX
    Explanations

    phrases and actions related to subscription and support for journalism

    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
    0:0.02
    1:0.02
    2:0.13
    3:0.17
    4:0.05
    5:0.03
    6:0.09
    7:0.05
    8:0.06
    9:0.07
    10:0.15
    11:0.11
    Negative Logits
    uthor
    -1.50
    trace
    -1.34
    hift
    -1.32
    alog
    -1.31
    axter
    -1.31
    eway
    -1.30
    tesy
    -1.28
    alogy
    -1.27
    ajor
    -1.27
    ilts
    -1.25
    POSITIVE LOGITS
    interstitial
    1.48
    �
    1.36
     Celeb
    1.33
    ��士
    1.32
     Celebr
    1.31
    Social
    1.31
     Meditation
    1.30
    Heart
    1.29
     Grammy
    1.25
    ゼ
    1.25
    Activations Density 0.008%

    No Known Activations