© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6961
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate duration or time spans

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.20
    4:0.04
    5:0.05
    6:0.02
    7:0.22
    8:0.05
    9:0.02
    10:0.22
    11:0.02
    Negative Logits
    Elsewhere
    -2.51
    Alternatively
    -2.36
    Secondly
    -2.29
     secondly
    -2.24
    Hyp
    -2.23
     Secondly
    -2.15
     Reaction
    -2.10
    Instead
    -2.05
    %:
    -2.04
    oids
    -2.04
    POSITIVE LOGITS
     YEAR
    2.78
     years
    2.76
     graduating
    2.65
    years
    2.59
     decades
    2.58
     decade
    2.53
    estern
    2.45
     franch
    2.40
     dating
    2.38
    undreds
    2.38
    Activations Density 0.025%

    No Known Activations