© 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. 22757
    Prev
    Next
    INDEX
    Explanations

    phrases related to having a physical representation of body parts in a text

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

    interactions involving tongue or lip movements

    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
    0:0.05
    1:0.03
    2:0.17
    3:0.05
    4:0.24
    5:0.04
    6:0.02
    7:0.04
    8:0.08
    9:0.16
    10:0.05
    11:0.02
    Negative Logits
    nee
    -1.50
    nw
    -1.38
    illac
    -1.34
    APS
    -1.34
    oresc
    -1.31
    cia
    -1.30
    YC
    -1.29
    Sit
    -1.28
    ources
    -1.27
    adelphia
    -1.26
    POSITIVE LOGITS
     Sloven
    1.39
     humor
    1.33
     Italians
    1.29
     irritation
    1.23
     centr
    1.22
     humour
    1.22
     tongues
    1.19
     exaggeration
    1.19
     Hungarian
    1.18
     whipping
    1.16
    Activations Density 0.002%

    No Known Activations