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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 22317
    Prev
    Next
    INDEX
    Explanations

    instances of personal experience or witness in narratives

    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
    1:0.04
    2:0.22
    3:0.08
    4:0.05
    5:0.10
    6:0.03
    7:0.04
    8:0.09
    9:0.12
    10:0.06
    11:0.04
    Negative Logits
    olor
    -1.40
     Advis
    -1.33
    rencies
    -1.31
    ominium
    -1.29
     Healer
    -1.25
     Telescope
    -1.25
    stals
    -1.24
    ramid
    -1.23
    livious
    -1.23
    drm
    -1.22
    POSITIVE LOGITS
    bole
    1.22
     unfavorable
    1.07
    و
    1.06
     suspense
    1.04
     leisure
    1.04
     disbelief
    1.02
     labor
    1.01
     accent
    1.01
    sing
    1.00
     ripe
    1.00
    Activations Density 0.000%

    No Known Activations