© 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. 3-ATT-KK
    11. 11996
    Prev
    Next
    INDEX
    Explanations

    unique words ending in 'er'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    various forms of suffixes and endings in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.04
    2:0.05
    3:0.32
    4:0.03
    5:0.03
    6:0.05
    7:0.20
    8:0.05
    9:0.05
    10:0.04
    11:0.05
    Negative Logits
    ailability
    -1.94
     裏�
    -1.49
    ritic
    -1.44
    ument
    -1.31
    scl
    -1.28
    urst
    -1.28
     teasp
    -1.27
    oola
    -1.26
    culus
    -1.25
    owl
    -1.23
    POSITIVE LOGITS
    vich
    1.44
     Gentleman
    1.31
     DISTRICT
    1.27
    rete
    1.25
     Myr
    1.22
    pta
    1.22
    ppe
    1.22
    lde
    1.19
     Fey
    1.18
     Username
    1.17
    Activations Density 0.004%

    No Known Activations