© 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. 43187
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.08
    1:0.12
    2:0.07
    3:0.08
    4:0.07
    5:0.07
    6:0.08
    7:0.09
    8:0.07
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     regress
    -2.04
    Mania
    -1.83
    Happy
    -1.76
    Magikarp
    -1.72
    agna
    -1.70
     kingdom
    -1.67
     sanity
    -1.66
     compan
    -1.66
    Mega
    -1.63
    Mor
    -1.61
    POSITIVE LOGITS
     Photograph
    1.91
     pictured
    1.86
     Letters
    1.85
     photographed
    1.80
     relayed
    1.79
     reprinted
    1.73
     Photos
    1.71
     conveyed
    1.65
     Desc
    1.64
     struck
    1.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.