© 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. 11989
    Prev
    Next
    INDEX
    Explanations

    phrases describing perception or realization, mostly related to personal experiences or observations

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

    assertions or statements about reality and evidence

    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
    0:0.02
    1:0.07
    2:0.08
    3:0.02
    4:0.01
    5:0.05
    6:0.37
    7:0.05
    8:0.03
    9:0.06
    10:0.07
    11:0.13
    Negative Logits
    imester
    -1.41
    ahime
    -1.37
    eka
    -1.32
    leneck
    -1.31
    rils
    -1.27
    edia
    -1.25
    vernment
    -1.25
     USL
    -1.23
     foe
    -1.21
    esan
    -1.20
    POSITIVE LOGITS
     except
    1.58
     horm
    1.40
    together
    1.39
     together
    1.22
     redund
    1.14
    except
    1.08
     redundancy
    1.08
    "}
    1.07
     besides
    1.04
    risome
    1.01
    Activations Density 0.271%

    No Known Activations