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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22159
    Prev
    Next
    INDEX
    Explanations

    phrases that convey feelings of observation or realization

    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
    0:0.09
    1:0.02
    2:0.12
    3:0.08
    4:0.04
    5:0.07
    6:0.04
    7:0.02
    8:0.28
    9:0.10
    10:0.05
    11:0.02
    Negative Logits
     Recomm
    -1.31
     Bearing
    -1.21
    atern
    -1.17
     ⓘ
    -1.13
    ufact
    -1.10
     sugg
    -1.07
    ascript
    -1.06
     Shares
    -1.02
     1903
    -0.99
     Cycling
    -0.99
    POSITIVE LOGITS
    argon
    1.34
     VIDEOS
    1.33
     firsthand
    1.25
    RAW
    1.24
    �
    1.24
    lag
    1.24
    natureconservancy
    1.23
    docs
    1.22
    soDeliveryDate
    1.20
    ideos
    1.19
    Activations Density 0.027%

    No Known Activations