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. 14068
    Prev
    Next
    INDEX
    Explanations

    text related to locations and actions taking place inside or outside

    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
    0:0.11
    1:0.03
    2:0.08
    3:0.16
    4:0.02
    5:0.09
    6:0.04
    7:0.03
    8:0.07
    9:0.20
    10:0.08
    11:0.03
    Negative Logits
    cedented
    -1.19
     ®
    -1.18
     DOI
    -1.15
    CVE
    -1.14
    Reviewer
    -1.13
    osate
    -1.09
     Towards
    -1.09
     Defeat
    -1.08
     Rita
    -1.08
    quished
    -1.08
    POSITIVE LOGITS
     lux
    1.31
     vents
    1.26
     entrances
    1.23
    paces
    1.23
     dens
    1.23
    brow
    1.22
    urb
    1.20
    esp
    1.19
    cup
    1.19
     encl
    1.18
    Activations Density 0.057%

    No Known Activations