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. 7390
    Prev
    Next
    INDEX
    Explanations

    concepts and terminology related to design and research methodology

    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
    1:0.03
    2:0.07
    3:0.04
    4:0.03
    5:0.12
    6:0.33
    7:0.02
    8:0.05
    9:0.11
    10:0.06
    11:0.06
    Negative Logits
     Seraph
    -1.39
     FANTASY
    -1.27
    velt
    -1.15
     Cruise
    -1.13
    NEWS
    -1.12
    apore
    -1.09
     Dusk
    -1.09
     Bots
    -1.09
    urnal
    -1.08
    IRD
    -1.08
    POSITIVE LOGITS
     hatched
    1.42
     itself
    1.42
    arching
    1.40
    etheless
    1.37
     incub
    1.29
    rium
    1.26
    ertodd
    1.24
    ioned
    1.23
    ciation
    1.22
    minus
    1.21
    Activations Density 0.441%

    No Known Activations