© 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. 5-ATT-KK
    11. 37366
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and variations related to context or position

    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
    1:0.02
    2:0.13
    3:0.05
    4:0.12
    5:0.02
    6:0.33
    7:0.04
    8:0.04
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    rament
    -1.27
    umbn
    -1.27
    enko
    -1.25
    rage
    -1.24
    eport
    -1.23
    ottage
    -1.20
    acco
    -1.18
    ricane
    -1.18
    ERO
    -1.16
    uries
    -1.16
    POSITIVE LOGITS
    etheless
    1.47
     perhaps
    1.44
    fortunately
    1.34
     preferably
    1.32
     excluding
    1.29
     presumably
    1.27
    despite
    1.24
     permitting
    1.23
     maybe
    1.22
     possibly
    1.20
    Activations Density 0.589%

    No Known Activations