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. 1-ATT-KK
    6. 6334
    Prev
    Next
    INDEX
    Explanations

    phrases related to community involvement or participation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.17
    2:0.07
    3:0.03
    4:0.11
    5:0.04
    6:0.03
    7:0.05
    8:0.03
    9:0.02
    10:0.06
    11:0.11
    Negative Logits
     respectively
    -1.36
     etc
    -1.35
     guiActiveUnfocused
    -1.34
     viz
    -1.30
    soever
    -1.26
     alike
    -1.22
    pmwiki
    -1.22
    DNA
    -1.22
    heres
    -1.19
     thereto
    -1.19
    POSITIVE LOGITS
    oshop
    1.38
    yss
    1.36
     FANTASY
    1.34
    ISE
    1.31
    lege
    1.30
     educate
    1.29
     THANK
    1.28
     thank
    1.27
    dress
    1.25
     Patreon
    1.24
    Activations Density 0.324%

    No Known Activations