© 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. 5-ATT-KK
    11. 35635
    Prev
    Next
    INDEX
    Explanations

    arguments related to marijuana legislation and social issues

    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
    0:0.26
    1:0.05
    2:0.12
    3:0.03
    4:0.06
    5:0.06
    6:0.02
    7:0.02
    8:0.17
    9:0.05
    10:0.04
    11:0.06
    Negative Logits
     [+
    -1.41
    opausal
    -1.40
    jected
    -1.39
    leeve
    -1.38
    rave
    -1.37
    heartedly
    -1.33
    fitted
    -1.32
    omorphic
    -1.32
    oeuv
    -1.30
     tape
    -1.29
    POSITIVE LOGITS
     etc
    2.19
    etc
    1.95
    userc
    1.64
    ��
    1.58
     Venice
    1.48
     achievements
    1.48
     Lastly
    1.47
    whatever
    1.45
     };
    1.45
     respectively
    1.44
    Activations Density 0.078%

    No Known Activations