© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22725
    Prev
    Next
    INDEX
    Explanations

    news articles about crime-related incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    content related to user subscriptions and email notifications

    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
    2:0.10
    3:0.11
    4:0.07
    5:0.11
    6:0.09
    7:0.03
    8:0.11
    9:0.15
    10:0.05
    11:0.02
    Negative Logits
    prototype
    -1.61
    oute
    -1.27
    sold
    -1.24
    ledged
    -1.23
    RP
    -1.22
    burgh
    -1.20
    pathy
    -1.19
    alk
    -1.17
    owship
    -1.15
    alky
    -1.11
    POSITIVE LOGITS
    Thumbnail
    1.47
     ensu
    1.38
    nw
    1.32
     mathemat
    1.22
    xxxxxxxx
    1.22
    Magikarp
    1.14
    glers
    1.12
    widget
    1.10
     tabl
    1.09
    odon
    1.08
    Activations Density 0.003%

    No Known Activations