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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43562
    Prev
    Next
    INDEX
    Explanations

    pronouns and conjunctions that indicate personal involvement or reference

    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
    2:0.09
    3:0.19
    4:0.12
    5:0.02
    6:0.11
    7:0.12
    8:0.05
    9:0.04
    10:0.06
    11:0.10
    Negative Logits
    WARE
    -1.44
    TPS
    -1.34
    Published
    -1.28
    turn
    -1.23
    lessly
    -1.22
     Discovery
    -1.21
    893
    -1.18
     undercut
    -1.17
    pak
    -1.16
     Instead
    -1.15
    POSITIVE LOGITS
    soDeliveryDate
    1.91
    omever
    1.60
    igham
    1.55
    %);
    1.48
    ishops
    1.46
    )"
    1.41
    ividual
    1.40
    ),"
    1.38
    ...)
    1.38
    )</
    1.35
    Activations Density 0.011%

    No Known Activations