© 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. 41175
    Prev
    Next
    INDEX
    Explanations

    phrases that include the words "as" and "like," often in comparative or descriptive contexts

    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
    1:0.01
    2:0.06
    3:0.07
    4:0.07
    5:0.03
    6:0.03
    7:0.31
    8:0.03
    9:0.03
    10:0.19
    11:0.09
    Negative Logits
     resides
    -1.66
     longitudinal
    -1.47
     manuscripts
    -1.46
     stere
    -1.44
    stra
    -1.40
     manuscript
    -1.39
     telescopes
    -1.39
    luck
    -1.38
     spiral
    -1.37
    Study
    -1.36
    POSITIVE LOGITS
    uggest
    1.93
    aco
    1.92
    aucas
    1.87
    anka
    1.82
    esty
    1.81
    obbies
    1.76
    clamation
    1.67
    ousy
    1.64
    afort
    1.57
    incerity
    1.57
    Activations Density 0.001%

    No Known Activations