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. 22316
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to sports or performance rankings

    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
    0:0.08
    1:0.06
    2:0.09
    3:0.08
    4:0.06
    5:0.08
    6:0.09
    7:0.07
    8:0.07
    9:0.10
    10:0.12
    11:0.04
    Negative Logits
    ️
    -1.76
    ngth
    -1.35
    afety
    -1.28
    �
    -1.07
     BALL
    -1.03
     positives
    -1.02
    oğ
    -1.01
    apons
    -0.99
     nodd
    -0.99
    ooters
    -0.99
    POSITIVE LOGITS
     respectively
    1.16
    )--
    1.14
     pard
    1.11
     Wesley
    1.09
    ope
    1.07
    !.
    1.00
     Jerusalem
    1.00
     tu
    1.00
    ).
    0.99
     accus
    0.98
    Activations Density 0.025%

    No Known Activations