© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44088
    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
    0:0.07
    1:0.05
    2:0.09
    3:0.08
    4:0.07
    5:0.09
    6:0.08
    7:0.08
    8:0.08
    9:0.09
    10:0.09
    11:0.08
    Negative Logits
     overload
    -1.78
    idth
    -1.63
    fficiency
    -1.52
     unchecked
    -1.50
    catch
    -1.49
    adequ
    -1.47
    atal
    -1.46
     typo
    -1.45
     skipping
    -1.45
     extingu
    -1.45
    POSITIVE LOGITS
    Gaming
    1.79
     Divinity
    1.69
     Fighters
    1.65
     Cheong
    1.65
    inav
    1.60
    Ranked
    1.56
    ORPG
    1.55
    Games
    1.55
     Blacks
    1.53
     Buk
    1.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.