© 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. 43420
    Prev
    Next
    INDEX
    Explanations

    numerical references and phrases indicating obligation or expectations

    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
    0:0.03
    1:0.01
    2:0.15
    3:0.42
    4:0.09
    5:0.02
    6:0.03
    7:0.03
    8:0.05
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
    apon
    -1.63
    ?」
    -1.61
     Pengu
    -1.52
    )—
    -1.52
     Shapiro
    -1.51
     Replay
    -1.51
    �
    -1.44
     someday
    -1.41
     Pulitzer
    -1.38
    ocalypse
    -1.34
    POSITIVE LOGITS
    Medium
    1.82
    ⓘ
    1.71
    Reviewer
    1.70
    APTER
    1.53
     VERY
    1.51
    :-
    1.46
     endif
    1.45
    Classic
    1.45
    OIL
    1.44
     realise
    1.43
    Activations Density 0.726%

    No Known Activations