© 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. 44144
    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
    1:0.07
    2:0.10
    3:0.09
    4:0.09
    5:0.08
    6:0.07
    7:0.07
    8:0.08
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     Atmosp
    -1.65
    Ire
    -1.62
    cember
    -1.50
     Cind
    -1.50
     persisted
    -1.48
    coins
    -1.47
     Orche
    -1.45
    TPS
    -1.43
    ecided
    -1.43
     Furn
    -1.42
    POSITIVE LOGITS
     milit
    1.53
     exempt
    1.50
    actionDate
    1.48
    arij
    1.45
    sterdam
    1.40
    license
    1.37
    problem
    1.36
     conflicts
    1.33
     domest
    1.31
     consent
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.