© 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. 9-ATT-KK
    6. 21303
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscription and email validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.01
    2:0.03
    3:0.10
    4:0.16
    5:0.06
    6:0.03
    7:0.11
    8:0.06
    9:0.01
    10:0.24
    11:0.02
    Negative Logits
     includ
    -2.43
     princ
    -2.37
     veget
    -2.31
    among
    -2.25
     purse
    -2.23
    minimum
    -2.08
     lett
    -2.08
    tein
    -2.05
     among
    -2.03
    itiz
    -1.99
    POSITIVE LOGITS
    ]);
    2.45
    wered
    2.35
     Gleaming
    2.33
    ��極
    2.30
     Error
    2.27
     Inferno
    2.26
     Alloy
    2.26
     Byte
    2.25
     ourselves
    2.24
     Ort
    2.19
    Activations Density 0.004%

    No Known Activations