© 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. 44153
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscription management and opting out of services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    0:0.01
    1:0.02
    2:0.07
    3:0.06
    4:0.05
    5:0.03
    6:0.31
    7:0.23
    8:0.04
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
     Windsor
    -1.33
    fal
    -1.27
    bats
    -1.26
     Stru
    -1.26
     LAT
    -1.26
     Prin
    -1.25
    KC
    -1.24
     woes
    -1.24
    ティ
    -1.23
     cents
    -1.23
    POSITIVE LOGITS
    arantine
    1.57
     expulsion
    1.48
    submit
    1.46
    apply
    1.39
    oshenko
    1.38
    agall
    1.37
    EStream
    1.36
     cance
    1.35
     placement
    1.35
    Accept
    1.34
    Activations Density 0.001%

    No Known Activations