© 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. 20113
    Prev
    Next
    INDEX
    Explanations

    statements regarding claims and arguments related to truth and validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.27
    3:0.11
    4:0.07
    5:0.03
    6:0.03
    7:0.04
    8:0.05
    9:0.06
    10:0.15
    11:0.11
    Negative Logits
     storage
    -1.61
     rece
    -1.59
     capacities
    -1.57
     asteroids
    -1.56
     batteries
    -1.47
     coffers
    -1.46
     perish
    -1.44
     capsules
    -1.44
     totaling
    -1.41
     fulfil
    -1.38
    POSITIVE LOGITS
    zsche
    1.96
    wav
    1.90
    zinski
    1.76
     naïve
    1.67
     infuri
    1.65
    ASY
    1.56
     puzzled
    1.56
     naive
    1.53
    ��
    1.52
    Solution
    1.50
    Activations Density 0.021%

    No Known Activations