© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35671
    Prev
    Next
    INDEX
    Explanations

    mentions of legislative bodies and related political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.09
    1:0.06
    2:0.04
    3:0.04
    4:0.05
    5:0.22
    6:0.05
    7:0.05
    8:0.03
    9:0.06
    10:0.12
    11:0.14
    Negative Logits
    zik
    -1.43
    oba
    -1.41
    seys
    -1.41
    iox
    -1.41
    roxy
    -1.38
    eton
    -1.38
    rika
    -1.37
    _-_
    -1.36
    atio
    -1.36
    zu
    -1.35
    POSITIVE LOGITS
     omn
    1.41
     exclusion
    1.35
     diver
    1.33
    wide
    1.26
     closure
    1.25
    �
    1.24
    ���
    1.23
     centrist
    1.23
     closures
    1.22
     consequential
    1.22
    Activations Density 0.004%

    No Known Activations