© 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. 22704
    Prev
    Next
    INDEX
    Explanations

    sequences related to descriptions of movements or actions

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

    phrases related to movement or transition

    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
    0:0.04
    1:0.02
    2:0.20
    3:0.04
    4:0.14
    5:0.04
    6:0.02
    7:0.02
    8:0.31
    9:0.08
    10:0.03
    11:0.01
    Negative Logits
    catentry
    -1.79
    chlor
    -1.48
    itu
    -1.44
    NT
    -1.39
    gemony
    -1.33
    raints
    -1.32
    iosyncr
    -1.31
    cision
    -1.31
    ictive
    -1.29
    nih
    -1.29
    POSITIVE LOGITS
     scrimmage
    1.59
     captcha
    1.51
     stall
    1.41
     stalls
    1.31
     gallery
    1.30
     backstage
    1.24
    ards
    1.23
     Auditor
    1.22
     distance
    1.22
     Gibraltar
    1.21
    Activations Density 0.013%

    No Known Activations