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. 7111
    Prev
    Next
    INDEX
    Explanations

    the presence of specific entities or organizations

    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
    2:0.11
    3:0.06
    4:0.24
    5:0.03
    6:0.10
    7:0.23
    8:0.02
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
    フォ
    -1.52
    Sea
    -1.47
    cellent
    -1.32
    amp
    -1.31
    arb
    -1.26
     Prices
    -1.26
    rament
    -1.25
    ulative
    -1.25
    oreal
    -1.25
    rimp
    -1.24
    POSITIVE LOGITS
     cryptoc
    1.43
     BMC
    1.43
     Seym
    1.39
     psyche
    1.38
     neighb
    1.36
     groove
    1.36
     circle
    1.33
     facade
    1.33
     cohesion
    1.31
     hierarchy
    1.31
    Activations Density 0.004%

    No Known Activations