© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 9363
    Prev
    Next
    INDEX
    Explanations

    specific Twitter handles and engagement with tweets

    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
    0:0.05
    1:0.02
    2:0.04
    3:0.36
    4:0.04
    5:0.06
    6:0.05
    7:0.06
    8:0.05
    9:0.06
    10:0.08
    11:0.08
    Negative Logits
     mountainous
    -2.35
     territ
    -2.29
     thereafter
    -2.10
    ,''
    -2.09
     markedly
    -2.09
     recurring
    -2.08
     withdrawn
    -2.04
     backward
    -2.04
     protracted
    -2.04
     fragmented
    -2.02
    POSITIVE LOGITS
     @
    3.33
    WF
    3.03
    Pope
    2.84
    CDC
    2.84
    @
    2.71
    DonaldTrump
    2.67
    WC
    2.56
    RIP
    2.53
    DCS
    2.53
    NBC
    2.48
    Activations Density 0.030%

    No Known Activations