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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10112
    Prev
    Next
    INDEX
    Explanations

    references to enrollment figures or participation statistics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.04
    4:0.03
    5:0.06
    6:0.08
    7:0.43
    8:0.05
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    ugu
    -1.59
    phrine
    -1.49
     sidx
    -1.36
    love
    -1.18
    ukong
    -1.18
    dinand
    -1.17
    etsk
    -1.15
    acting
    -1.10
    izza
    -1.08
    leys
    -1.08
    POSITIVE LOGITS
     contingent
    1.14
     dwindling
    1.08
     dictated
    1.08
     minimized
    1.07
     diminished
    1.07
     requisite
    1.06
     Houth
    1.05
     Presence
    1.05
     Heist
    1.05
     asymm
    1.05
    Activations Density 0.093%

    No Known Activations