© 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. 2-ATT-KK
    11. 21844
    Prev
    Next
    INDEX
    Explanations

    discussions related to legal protections and judicial decisions surrounding the First Amendment and privacy rights

    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
    0:0.06
    1:0.11
    2:0.04
    3:0.05
    4:0.04
    5:0.07
    6:0.09
    7:0.11
    8:0.06
    9:0.12
    10:0.14
    11:0.06
    Negative Logits
    onut
    -1.37
    peak
    -1.35
    ngth
    -1.33
    stretched
    -1.31
    orthern
    -1.28
     flares
    -1.24
    doms
    -1.23
     diarr
    -1.22
     apologise
    -1.20
    ️
    -1.19
    POSITIVE LOGITS
     Plaintiff
    1.80
     petitioner
    1.72
     lawfully
    1.64
     Defendant
    1.59
     plaintiff
    1.59
     Defendants
    1.56
     §
    1.54
     appellant
    1.54
     unconstitutional
    1.53
     Plaint
    1.53
    Activations Density 0.312%

    No Known Activations