© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43702
    Prev
    Next
    INDEX
    Explanations

    interactions involving communication and insurance-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.08
    3:0.13
    4:0.06
    5:0.04
    6:0.02
    7:0.04
    8:0.06
    9:0.09
    10:0.23
    11:0.16
    Negative Logits
     historically
    -1.28
     ensemble
    -1.26
    efeated
    -1.25
    zbollah
    -1.11
    inctions
    -1.10
    opoly
    -1.09
     intrinsically
    -1.05
     sustainability
    -1.04
     disproportionately
    -1.04
    Adapt
    -1.02
    POSITIVE LOGITS
    upon
    1.38
     promptly
    1.36
    then
    1.33
    IRC
    1.31
    SPONSORED
    1.31
    Phone
    1.27
    Fill
    1.18
    REDACTED
    1.17
    mop
    1.12
     immediately
    1.12
    Activations Density 1.110%

    No Known Activations