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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44194
    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
    0:0.06
    1:0.07
    2:0.09
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.07
    10:0.09
    11:0.09
    Negative Logits
    atography
    -1.64
    Sources
    -1.48
    aunder
    -1.48
     Burr
    -1.42
    ohyd
    -1.42
     Thick
    -1.42
    hal
    -1.42
    theme
    -1.38
    adium
    -1.36
    akespeare
    -1.36
    POSITIVE LOGITS
    ADRA
    2.14
     describ
    1.71
    STAT
    1.68
    BIL
    1.66
    76561
    1.63
    00007
    1.61
    WAR
    1.58
    zona
    1.58
    8000
    1.50
    warn
    1.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.