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. 2-ATT-KK
    6. 14063
    Prev
    Next
    INDEX
    Explanations

    terms related to benefits and drawbacks

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.05
    1:0.03
    2:0.24
    3:0.08
    4:0.09
    5:0.07
    6:0.03
    7:0.03
    8:0.07
    9:0.17
    10:0.05
    11:0.03
    Negative Logits
    ��
    -2.13
    ById
    -1.41
    ヴァ
    -1.30
     ILCS
    -1.22
     Hollow
    -1.20
     Swamp
    -1.20
    Leaks
    -1.17
    bats
    -1.12
    ��士
    -1.11
    prototype
    -1.10
    POSITIVE LOGITS
    zai
    1.45
    ctive
    1.44
    cially
    1.30
    ffect
    1.29
    ELY
    1.26
    orsi
    1.24
    ajor
    1.23
    phrine
    1.22
    ult
    1.21
    hel
    1.20
    Activations Density 0.002%

    No Known Activations