© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21698
    Prev
    Next
    INDEX
    Explanations

    comparisons and references to relative statistics or quantities

    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
    1:0.03
    2:0.09
    3:0.08
    4:0.04
    5:0.11
    6:0.05
    7:0.06
    8:0.17
    9:0.07
    10:0.11
    11:0.05
    Negative Logits
    ¯¯¯¯¯¯¯¯
    -1.31
    minist
    -1.21
    者
    -1.16
    istrate
    -1.16
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -1.13
     Hotel
    -1.12
     Springs
    -1.07
    ittee
    -1.06
     Fork
    -1.05
    Frameworks
    -1.05
    POSITIVE LOGITS
    ahime
    1.19
    BuyableInstoreAndOnline
    1.14
     propensity
    1.10
    trak
    1.03
     prevalence
    1.02
     levels
    1.01
     standpoint
    0.97
     totality
    0.96
     hypothetical
    0.95
     perspective
    0.95
    Activations Density 0.044%

    No Known Activations