© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28464
    Prev
    Next
    INDEX
    Explanations

    questions related to entertainment news and programming details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.17
    3:0.15
    4:0.11
    5:0.03
    6:0.09
    7:0.05
    8:0.06
    9:0.05
    10:0.08
    11:0.10
    Negative Logits
    gio
    -1.57
    gged
    -1.52
    ゴン
    -1.43
    Reloaded
    -1.43
    rontal
    -1.38
    othal
    -1.38
     Curve
    -1.36
    Phill
    -1.22
    retty
    -1.22
     Ratio
    -1.19
    POSITIVE LOGITS
     strives
    1.40
    interstitial
    1.30
    achu
    1.30
    bleacher
    1.30
    wealth
    1.28
     GeForce
    1.25
    orthern
    1.24
    please
    1.23
     invests
    1.23
     beverage
    1.23
    Activations Density 0.000%

    No Known Activations