© 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. 43293
    Prev
    Next
    INDEX
    Explanations

    prominent names and terms associated with political figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.13
    1:0.31
    2:0.05
    3:0.04
    4:0.04
    5:0.20
    6:0.02
    7:0.02
    8:0.04
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
    obin
    -1.68
     immunity
    -1.63
    illary
    -1.60
     endanger
    -1.60
     cultivate
    -1.57
    agame
    -1.54
     privilege
    -1.53
    cause
    -1.52
    ocation
    -1.52
    problem
    -1.50
    POSITIVE LOGITS
     (@
    2.62
    Enlarge
    1.96
    @
    1.93
     >>
    1.87
     (~
    1.82
    ��
    1.82
     <+
    1.77
    ©
    1.76
    >>
    1.74
     (.
    1.72
    Activations Density 0.002%

    No Known Activations