© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-ATT-KK
    11. 43758
    Prev
    Next
    INDEX
    Explanations

    expressions of potentiality and effects, especially in relation to actions and outcomes

    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
    2:0.08
    3:0.13
    4:0.08
    5:0.04
    6:0.31
    7:0.06
    8:0.03
    9:0.04
    10:0.07
    11:0.08
    Negative Logits
     Ys
    -1.38
    ITNESS
    -1.34
    atform
    -1.33
    terday
    -1.26
    wolves
    -1.22
    gaard
    -1.20
    ashi
    -1.19
     Zak
    -1.18
     Ruk
    -1.17
    gemony
    -1.16
    POSITIVE LOGITS
    odder
    1.59
     depending
    1.57
    depending
    1.52
     easily
    1.41
     siph
    1.34
    taboola
    1.33
     quite
    1.33
    gettable
    1.32
    xtap
    1.29
     Depending
    1.26
    Activations Density 0.111%

    No Known Activations