© 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. 43133
    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
    1:0.07
    2:0.09
    3:0.08
    4:0.08
    5:0.08
    6:0.06
    7:0.10
    8:0.08
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
    akeru
    -1.95
    idth
    -1.69
    swer
    -1.64
     JUSTICE
    -1.49
     dated
    -1.43
    acters
    -1.42
     ascert
    -1.41
     conjecture
    -1.41
     illustrated
    -1.39
     inaccur
    -1.39
    POSITIVE LOGITS
    �
    1.74
    Female
    1.70
    frog
    1.68
    Alert
    1.67
     Alert
    1.67
    bird
    1.66
    Male
    1.66
    fly
    1.65
    Thu
    1.64
    cue
    1.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.