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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2021
    Prev
    Next
    INDEX
    Explanations

    statements about confirmations related to reports or news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.06
    3:0.21
    4:0.03
    5:0.08
    6:0.03
    7:0.04
    8:0.03
    9:0.03
    10:0.33
    11:0.03
    Negative Logits
    quer
    -2.24
    ]]
    -2.21
    }}}
    -2.16
    usterity
    -2.15
    �
    -2.12
    �
    -2.11
    �
    -2.10
    yrs
    -2.10
    ̶
    -2.10
    ptin
    -2.08
    POSITIVE LOGITS
     confirmed
    2.46
     confirms
    2.45
     findings
    2.45
     reports
    2.22
     receipt
    2.22
     sighting
    2.17
     coordinates
    2.16
     credentials
    2.13
     corrobor
    2.11
     via
    2.06
    Activations Density 0.063%

    No Known Activations