© 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. 37957
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to verification and substantiation of claims

    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
    1:0.02
    2:0.05
    3:0.06
    4:0.18
    5:0.03
    6:0.04
    7:0.32
    8:0.03
    9:0.03
    10:0.07
    11:0.09
    Negative Logits
    ーティ
    -1.63
    ドラ
    -1.63
    ワ
    -1.57
     Thumbnails
    -1.54
    thumbnails
    -1.45
    ヘ
    -1.42
    ━
    -1.39
    sembly
    -1.37
    ツ
    -1.33
    ircraft
    -1.33
    POSITIVE LOGITS
     assertions
    1.75
     belief
    1.65
     claims
    1.62
     claim
    1.61
     factual
    1.61
     hypotheses
    1.57
     suspicions
    1.56
     unfounded
    1.56
     hypothesis
    1.56
     rumours
    1.55
    Activations Density 0.003%

    No Known Activations