Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44035
    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
    0:0.10
    1:0.07
    2:0.09
    3:0.08
    4:0.07
    5:0.08
    6:0.07
    7:0.09
    8:0.09
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
    ufact
    -1.88
    ebted
    -1.82
    romeda
    -1.79
    ambers
    -1.72
    ertodd
    -1.66
    iris
    -1.63
    omnia
    -1.61
     Bir
    -1.56
    uggle
    -1.55
     Olympia
    -1.53
    POSITIVE LOGITS
     gust
    1.54
    76561
    1.45
     (@
    1.44
    etime
    1.43
     outp
    1.41
     redistributed
    1.40
     dex
    1.40
    ede
    1.37
    pmwiki
    1.36
    ensity
    1.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.