© 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. 42714
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscription prompts and continuing to read content

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.06
    4:0.07
    5:0.05
    6:0.37
    7:0.03
    8:0.07
    9:0.07
    10:0.07
    11:0.03
    Negative Logits
    oi
    -1.27
    ahime
    -1.18
     palm
    -1.17
    ️
    -1.16
     transitioning
    -1.16
    VILLE
    -1.16
    ennial
    -1.14
     mans
    -1.13
     sim
    -1.13
    stros
    -1.12
    POSITIVE LOGITS
     millenn
    1.47
    anyahu
    1.36
     teasp
    1.32
    govtrack
    1.30
    Impl
    1.29
    ��
    1.25
    �
    1.25
     exting
    1.23
    rocal
    1.23
    Streamer
    1.22
    Activations Density 0.001%

    No Known Activations