© 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. 40915
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "for" indicating purpose or responsibility

    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
    0:0.04
    1:0.00
    2:0.09
    3:0.04
    4:0.13
    5:0.02
    6:0.07
    7:0.29
    8:0.03
    9:0.03
    10:0.08
    11:0.12
    Negative Logits
    urances
    -1.73
     sincerity
    -1.53
    thodox
    -1.35
    shapeshifter
    -1.30
    ure
    -1.29
    ardless
    -1.28
     scrimmage
    -1.27
    incerity
    -1.27
    vern
    -1.27
     pessim
    -1.26
    POSITIVE LOGITS
     stolen
    1.36
    =/
    1.29
     WATCH
    1.27
     scrap
    1.25
     Wer
    1.24
     Tracking
    1.21
     offence
    1.17
     EE
    1.17
     Damage
    1.15
     LW
    1.13
    Activations Density 0.010%

    No Known Activations