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. 18781
    Prev
    Next
    INDEX
    Explanations

    elements related to new product releases and updates in technology

    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
    0:0.06
    1:0.06
    2:0.01
    3:0.17
    4:0.04
    5:0.14
    6:0.13
    7:0.02
    8:0.11
    9:0.19
    10:0.01
    11:0.02
    Negative Logits
    EStream
    -2.20
    �醒
    -2.13
    hower
    -1.98
    "}
    -1.84
    anamo
    -1.77
    gew
    -1.72
    wagon
    -1.71
    fman
    -1.71
     UNCLASSIFIED
    -1.69
    dinand
    -1.69
    POSITIVE LOGITS
     2019
    2.03
     Deadline
    1.86
     standalone
    1.82
     debut
    1.82
     debuted
    1.78
     Xperia
    1.75
     futuristic
    1.75
     curated
    1.75
     feature
    1.72
     2018
    1.72
    Activations Density 0.616%

    No Known Activations