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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22313
    Prev
    Next
    INDEX
    Explanations

    terms related to microcephaly and its association with various medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.16
    3:0.22
    4:0.04
    5:0.10
    6:0.02
    7:0.03
    8:0.06
    9:0.12
    10:0.07
    11:0.03
    Negative Logits
    imar
    -1.21
    cember
    -1.05
    yip
    -1.05
     erection
    -1.02
    ouk
    -1.01
    heimer
    -1.01
     AUTH
    -1.00
    artist
    -0.99
     Kem
    -0.97
     FALSE
    -0.95
    POSITIVE LOGITS
    adelphia
    1.33
    ader
    1.27
    isc
    1.21
    system
    1.15
    uder
    1.12
    adium
    1.10
    ature
    1.08
    isks
    1.07
    opter
    1.04
    rocket
    1.04
    Activations Density 0.016%

    No Known Activations